Explore advancements in
Machine Learning

All research

- A – Z
- Z – A
- Newest
- Oldest

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference ICLRPublished year 2025
AuthorsYusu Qian, Hanrong Ye, Jean-Philippe Fauconnier, Peter Grasch, Yinfei Yang, Zhe Gan
Evaluating Sample Utility for Data Selection by Mimicking Model Weights
content type paper research area Computer Vision, research area Data Science and AnnotationPublished year 2025
AuthorsTzu-Heng Huang, Manjot Bilkhu, Frederic Sala, Javier Movellan
Grounding Multimodal Large Language Models in Actions
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2025
AuthorsAndrew Szot, Bogdan Mazoure, Harsh Agrawal, Devon Hjelm, Zsolt Kira, Alexander Toshev
Wearable Accelerometer Foundation Models for Health via Knowledge Distillation
content type paper research area Health, research area Methods and AlgorithmsPublished year 2025
AuthorsSalar Abbaspourazad, Anshuman Mishra, Joseph Futoma, Andrew C. Miller, Ian Shapiro
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
content type paper research area Computer VisionPublished year 2025
AuthorsRoman Bachmann*†‡, Jesse Allardice*, David Mizrahi*, Enrico Fini, Oğuzhan Fatih Kar‡, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir‡, Afshin Dehghan
From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2025
AuthorsAndrew Szot, Bogdan Mazoure, Omar Attia, Aleksei Timofeev, Harsh Agrawal, Devon Hjelm, Zhe Gan, Zsolt Kira, Alexander Toshev
KV Prediction for Improved Time to First Token
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2025
AuthorsMaxwell Horton, Qingqing Cao, Chenfan Sun, Yanzi Jin, Sachin Mehta, Mohammad Rastegari, Moin Nabi
Transfer Learning in Scalable Graph Neural Network for Improved Physical Simulation
content type paper research area Methods and Algorithms, research area Tools, Platforms, FrameworksPublished year 2025
AuthorsSiqi Shen, Yu Liu, Daniel Biggs, Omar Hafez, Jiandong Yu, Wentao Zhang, Bin Cui, Jiulong Shan
ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning
content type paper research area Methods and AlgorithmsPublished year 2025
AuthorsDaehwa Kim, Mario Srouji, Chen Chen, Jian Zhang
Robust Autonomy Emerges from Self-Play
content type paper research area Methods and AlgorithmsPublished year 2025
AuthorsMarco Cusumano-Towner, David Hafner, Alex Hertzberg, Brody Huval, Aleksei Petrenko, Eugene Vinitsky, Erik Wijmans, Taylor Killian, Stuart Bowers, Ozan Sener, Philipp Krähenbühl, Vladlen Koltun

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference ICLRPublished year 2025
AuthorsYusu Qian, Hanrong Ye, Jean-Philippe Fauconnier, Peter Grasch, Yinfei Yang, Zhe Gan
Evaluating Sample Utility for Data Selection by Mimicking Model Weights
content type paper research area Computer Vision, research area Data Science and AnnotationPublished year 2025
AuthorsTzu-Heng Huang, Manjot Bilkhu, Frederic Sala, Javier Movellan
Grounding Multimodal Large Language Models in Actions
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2025
AuthorsAndrew Szot, Bogdan Mazoure, Harsh Agrawal, Devon Hjelm, Zsolt Kira, Alexander Toshev
Wearable Accelerometer Foundation Models for Health via Knowledge Distillation
content type paper research area Health, research area Methods and AlgorithmsPublished year 2025
AuthorsSalar Abbaspourazad, Anshuman Mishra, Joseph Futoma, Andrew C. Miller, Ian Shapiro
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
content type paper research area Computer VisionPublished year 2025
AuthorsRoman Bachmann*†‡, Jesse Allardice*, David Mizrahi*, Enrico Fini, Oğuzhan Fatih Kar‡, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir‡, Afshin Dehghan
From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2025
AuthorsAndrew Szot, Bogdan Mazoure, Omar Attia, Aleksei Timofeev, Harsh Agrawal, Devon Hjelm, Zhe Gan, Zsolt Kira, Alexander Toshev
KV Prediction for Improved Time to First Token
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2025
AuthorsMaxwell Horton, Qingqing Cao, Chenfan Sun, Yanzi Jin, Sachin Mehta, Mohammad Rastegari, Moin Nabi
Transfer Learning in Scalable Graph Neural Network for Improved Physical Simulation
content type paper research area Methods and Algorithms, research area Tools, Platforms, FrameworksPublished year 2025
AuthorsSiqi Shen, Yu Liu, Daniel Biggs, Omar Hafez, Jiandong Yu, Wentao Zhang, Bin Cui, Jiulong Shan
ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning
content type paper research area Methods and AlgorithmsPublished year 2025
AuthorsDaehwa Kim, Mario Srouji, Chen Chen, Jian Zhang
Robust Autonomy Emerges from Self-Play
content type paper research area Methods and AlgorithmsPublished year 2025
AuthorsMarco Cusumano-Towner, David Hafner, Alex Hertzberg, Brody Huval, Aleksei Petrenko, Eugene Vinitsky, Erik Wijmans, Taylor Killian, Stuart Bowers, Ozan Sener, Philipp Krähenbühl, Vladlen Koltun
Findings of the IWSLT 2024 Evaluation Campaign
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2025
ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICASSPPublished year 2025
AuthorsMojtaba Heydari, Mehrez Souden, Bruno Conejo, Joshua Atkins
Private Federated Learning In Real World Application – A Case Study
content type paper research area Methods and Algorithms, research area PrivacyPublished year 2025
AuthorsAn Ji, Bortik Bandyopadhyay, Congzheng Song, Natarajan Krishnaswami, Prabal Vashisht, Rigel Smiroldo, Isabel Litton, Sayantan Mahinder, Mona Chitnis, Andrew W Hill
Theory, Analysis, and Best Practices for Sigmoid Self-Attention
content type paper research area Methods and Algorithmsconference ICLRPublished year 2025
AuthorsJason Ramapuram*, Federico Danieli*, Eeshan Gunesh Dhekane*, Floris Weers*, Dan Busbridge*, Pierre Ablin*, Tatiana Likhomanenko*, Jagrit Digani, Zijin Gu, Amitis Shidani, Russ Webb
Cut Your Losses in Large-Vocabulary Language Models
content type paper research area Methods and Algorithmsconference ICLRPublished year 2025
AuthorsErik Wijmans, Brody Huval, Alexander Hertzberg, Vladlen Koltun, Philipp Krähenbühl
eaSEL: Promoting Social-Emotional Learning and Parent-Child Interaction Through AI-Mediated Content Consumption
content type paper research area Human-Computer Interactionconference CHIPublished year 2025
AuthorsJocelyn Shen, Jennifer King Chen, Leah Findlater, Griffin Dietz Smith
Reinforcement Learning for Long-Horizon Interactive LLM Agents
content type paper research area Methods and AlgorithmsPublished year 2025
AuthorsKevin Chen, Marco Cusumano-Towner, Brody Huval, Aleksei Petrenko, Jackson Hamburger, Vladlen Koltun, Philipp Krähenbühl
Adaptive Training Distributions with Scalable Online Bilevel Optimization
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingTransactions on Machine Learning Research (TMLR)Published year 2025
AuthorsDavid Grangier, Pierre Ablin, Awni Hannun
Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICLRPublished year 2025
AuthorsShengyu Feng, Xiang Kong, Shuang Ma, Aonan Zhang, Dong Yin, Chong Wang, Ruoming Pang, Yiming Yang
Compact Neural TTS Voices for Accessibility
content type paper research area Accessibility, research area Speech and Natural Language Processingconference ICASSPPublished year 2025
AuthorsKunal Jain, Eoin Murphy, Deepanshu Gupta, Jonathan Dyke, Saumya Shah, Vasilieios Tsiaras, Petko Petkov, Alistair Conkie
Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization
content type paper research area Speech and Natural Language Processingconference NAACLPublished year 2025
AuthorsZilu Tang, Rajen Chatterjee, Sarthak Garg
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2025
AuthorsSamira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin Mohamed Elnouby Ali, Josh Susskind, Vimal Thilak
Provable Uncertainty Decomposition via Higher-Order Calibration
content type paper research area Methods and Algorithmsconference ICLRPublished year 2025
AuthorsGustaf Ahdritz, Aravind Gollakota, Parikshit Gopalan, Charlotte Peale, Udi Wieder
ELEGNT: Expressive and Functional Movement Design for Non-Anthropomorphic Robot
content type paper research area Human-Computer InteractionPublished year 2025
AuthorsYuhan Hu, Peide Huang, Mouli Sivapurapu, Jian Zhang
EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning
content type paper research area Human-Computer InteractionPublished year 2025
AuthorsPeide Huang, Yuhan Hu, Nataliya Nechyporenko, Daehwa Kim, Walter Talbott, Jian Zhang
Mapping Cells Through Time and Space With Moscot
content type paper research area Health, research area Methods and Algorithmsconference NaturePublished year 2025
AuthorsDominik Klein†‡**, Giovanni Palla†‡, Marius Lange†‡§, Michal Klein, Zoe Piran¶**, Manuel Gander†, Laetitia Meng-Papaxanthos††, Michael Sterr†, Aimée Bastidas-Ponce†, Marta Tarquis-Medina†, Heiko Lickert†‡, Mostafa Bakhti†, Mor Nitzan¶, Marco Cuturi, Fabian J. Theis†‡
Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2025
AuthorsTakaaki Hori, Martin Kocour, Adnan Haider, Erik McDermott, Xiaodan Zhuang
DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models
content type paper research area Computer VisionPublished year 2025
AuthorsKevin Miao, Harsh Agrawal, Qihang Zhang, Federico Semeraro, Marco Cavallo, Jiatao Gu, Alexander Toshev
On the Modeling Capabilities of Large Language Models for Sequential Decision Making
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2025
AuthorsMartin Klissarov, Devon Hjelm, Alexander Toshev, Bogdan Mazoure
Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts
content type paper research area Computer Vision, research area Methods and AlgorithmsTransactions on Machine Learning Research (TMLR)Published year 2025
AuthorsJonathan Crabbé, Pau Rodríguez, Vaishaal Shankar, Luca Zappella, Arno Blaas
Controlling Language and Diffusion Models by Transporting Activations
content type paper research area Methods and AlgorithmsPublished year 2025
AuthorsPau Rodriguez, Arno Blaas, Michal Klein, Luca Zappella, Nicholas Apostoloff, Marco Cuturi, Xavier Suau
KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference COLINGPublished year 2025
AuthorsZelin Zhou, Simone Conia, Daniel Lee, Min Li, Shenglei Huang, Umar Farooq Minhas, Saloni Potdar, Henry Xiao, Yunyao Li
Fingerprinting Codes Meet Geometry: Improved Lower Bounds for Private Query Release and Adaptive Data Analysis
content type paper research area Methods and Algorithms, research area PrivacyPublished year 2025
AuthorsXin Lyu, Kunal Talwar
Privacy-Computation Trade-offs in Private Repetition and Metaselection
content type paper research area Methods and Algorithms, research area Privacyconference FORCPublished year 2025
AuthorsKunal Talwar
SLiCK: Exploiting Subsequences for Length-Constrained Keyword Spotting
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICASSPPublished year 2025
AuthorsKumari Nishu, Minsik Cho, Devang Naik
3D Shape Tokenization
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2025
AuthorsRick Chang, Yuyang Wang, Miguel Angel Bautista Martin, Jiatao Gu, Josh Susskind, Oncel Tuzel
Accelerating LLM Inference on NVIDIA GPUs with ReDrafter
content type highlightPublished year 2024
ARMADA: Augmented Reality for Robot Manipulation and Robot-Free Data Acquisition
content type paper research area Data Science and Annotation, research area Human-Computer InteractionPublished year 2024
AuthorsNataliya Nechyporenko, Ryan Hoque, Christopher Webb, Mouli Sivapurapu, Jian Zhang
BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale
content type paper research area Knowledge Bases and Search, research area Methods and Algorithmsconference AAAIPublished year 2024
AuthorsRandy Ardywibowo, Rakesh Sunki, Lucy Kuo, Sankalp Nayak
Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models
content type paper research area Fairness, research area Speech and Natural Language Processingconference NeurIPSPublished year 2024
AuthorsNatalie Mackraz*, Nivedha Sivakumar*, Samira Khorshidi, Krishna Patel, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff
Learning Spatially-Aware Language and Audio Embeddings
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference NeurIPSPublished year 2024
AuthorsBhavika Devnani, Skyler Seto, Zakaria Aldeneh, Alessandro Toso, Elena Menyaylenko, Barry-John Theobald, Jonathan Sheaffer, Miguel Sarabia
Momentum Approximation in Asynchronous Private Federated Learning
content type paper research area PrivacyWorkshop at NeurIPSPublished year 2024
AuthorsTao Yu, Congzheng Song, Jianyu Wang, Mona Chitnis
Apple Machine Learning Research at NeurIPS 2024
content type highlightPublished year 2024
How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsYusu Qian, Haotian Zhang, Yinfei Yang, Zhe Gan
Private and Personalized Frequency Estimation in a Federated Setting
content type paper research area Methods and Algorithms, research area Privacyconference NeurIPSPublished year 2024
AuthorsAmrith Setlur, Vitaly Feldman, Kunal Talwar
SALSA: Soup-Based Alignment Learning for Stronger Adaptation in RLHF
content type paper research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsAtoosa Chegini, Hamid Kazemi, Iman Mirzadeh, Dong Yin, Maxwell Horton, Moin Nabi, Mehrdad Farajtabar, Keivan Alizadeh
Classifier-Free Guidance Is a Predictor-Corrector
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2024
AuthorsArwen Bradley, Preetum Nakkiran
GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsDominik Klein, Théo Uscidda, Fabian Theis, Marco Cuturi Cameto
Learning Elastic Costs to Shape Monge Displacements
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsMichal Klein, Aram-Alexandre Pooladian, Pierre Ablin, Eugène Ndiaye, Jonathan Niles-Weed, Marco Cuturi Cameto
Leveraging Periodicity for Robustness with Multi-modal Mood Pattern Models
content type paper research area Health, research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsJaya Narain*, Jenny Sun*, Oussama Elachqar, Haraldur Hallgrimsson, Feng Zhu, Shirley Ren
Strategic Linear Contextual Bandits
content type paper research area Knowledge Bases and Search, research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsThomas Kleine Buening, Aadirupa Saha, Christos Dimitrakakis, Haifeng Xu
Towards Time-Series Reasoning with LLMs
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference NeurIPSPublished year 2024
AuthorsWinnie Chow, Lauren Gardiner, Haraldur T. Hallgrímsson, Maxwell A. Xu, Shirley You Ren
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsJiatao Gu, Ying Shen, Shuangfei Zhai, Yizhe Zhang, Navdeep Jaitly, Joshua M. Susskind
Speech is More Than Words: Do Speech-to-Text Translation Systems Leverage Prosody?
content type paper research area Speech and Natural Language ProcessingWorkshop at EMNLPPublished year 2024
AuthorsYiannis Tsiamas, Matthias Sperber, Andrew Finch, Sarthak Garg
Efficient and Effective Uncertainty Quantification in LLMs
content type paper research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsMiao Xiong, Andrea Santilli, Michael Kirchhof, Adam Golinski, Sinead Williamson
Instance-Optimal Private Density Estimation in the Wasserstein Distance
content type paper research area Privacyconference NeurIPSPublished year 2024
AuthorsVitaly Feldman, Audra McMillan, Satchit Sivakumar, Kunal Talwar
Memory-Retaining Finetuning via Distillation
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsZitong Yang, Aonan Zhang, Sam Wiseman, Xiang Kong, Ke Ye, Dong Yin
Multimodal Autoregressive Pre-Training of Large Vision Encoders
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2024
AuthorsEnrico Fini*, Mustafa Shukor*, Xiujun Li, Philipp Dufter, Michal Klein, David Haldimann, Sai Aitharaju, Louis Béthune, Zhe Gan, Victor Turrisi, Alexander Toshev, Marcin Eichner, Yinfei Yang, Moin Nabi, Josh Susskind, Alaaeldin El-Nouby*
Do LLMs Estimate Uncertainty Well in Instruction-Following?
content type paper research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsJuyeon Heo, Miao Xiong, Christina Heinze-Deml, Jaya Narain
Do LLMs Internally "Know" When They Follow Instructions?
content type paper research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsJuyeon Heo, Christina Heinze-Deml, Oussama Elachqar, Shirley Ren, Udhay Nallasamy, Andy Miller, Kwan Ho Ryan Chan, Jaya Narain
Faster Algorithms for User-Level Private Stochastic Convex Optimization
content type paper research area Methods and Algorithms, research area Privacyconference NeurIPSPublished year 2024
AuthorsAndrew Lowy, Daogao Liu, Hilal Asi
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsEtai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang, Joshua Susskind
Private Online Learning via Lazy Algorithms
content type paper research area Methods and Algorithms, research area Privacyconference NeurIPSPublished year 2024
AuthorsHilal Asi, Tomer Koren, Daogao Liu, Kunal Talwar
Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
content type paper research area Methods and Algorithms, research area Privacyconference NeurIPSPublished year 2024
AuthorsHilal Asi, Daogao Liu, Kevin Tian
Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsOmar Montasser, Han Shao, Emmanuel Abbe
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference NeurIPSPublished year 2024
AuthorsHadi Pour Ansari, Chun-Liang Li, Rick Chang, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, Oncel Tuzel
Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications
content type paper research area Methods and Algorithms, research area Tools, Platforms, FrameworksWorkshop at NeurIPSPublished year 2024
AuthorsScott Hoang, Minsik Cho, Thomas Merth, Atlas Wang, Mohammad Rastegari, Devang Naik
Speculative Streaming: Fast LLM Inference Without Auxiliary Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsNikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Mohammad Rastegari, Mahyar Najibi
Towards Low-Bit Communication for Tensor Parallel LLM Inference
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsHarry Dong, Tyler Johnson, Minsik Cho, Emad Soroush
Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models
content type paper research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsKeivan Alizadeh, Iman Mirzadeh, Hooman Shahrokhi, Dmitry Belenko, Frank Sun, Minsik Cho, Mohammad Hossein Sekhavat, Moin Nabi, Mehrdad Farajtabar
Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2024
AuthorsEtai Littwin, Vimal Thilak, Anand Gopalakrishnan
Generalization on the Unseen, Logic Reasoning and Degree Curriculum
content type paper research area Methods and Algorithmsconference Journal of Machine Learning Research (JMLR)Published year 2024
AuthorsEmmanuel Abbe, Samy Bengio, Aryo Lotfi, Kevin Rizk
Recurrent Drafter for Fast Speculative Decoding in Large Language Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsAonan Zhang, Ray Zhang, Yunfei Cheng, Chong Wang, Yi Wang
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsMohammad Samragh, Iman Mirzadeh, Keivan Alizadeh Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar
Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models
content type paper research area Human-Computer Interaction, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsOggi Rudovic, Pranay Dighe, Yi Su, Vineet Garg, Sameer Dharur, Xiaochuan Niu, Ahmed H. Abdelaziz, Saurabh Adya, Ahmed Tewfik
Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval
content type paper research area Speech and Natural Language ProcessingIEEE Spoken Language Technology Workshop (SLT)Published year 2024
AuthorsNikolaos Flemotomos, Roger Hsiao, Pawel Swietojanski, Takaaki Hori, Dogan Can, Xiaodan Zhuang
Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsChen Huang, Skyler Seto, Samira Abnar, David Grangier, Navdeep Jaitly, Josh Susskind
On Device Llama 3.1 with Core ML
content type highlightPublished year 2024
Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs
content type paper research area Knowledge Bases and Search, research area Methods and Algorithms, research area Speech and Natural Language Processingconference EMNLPPublished year 2024
AuthorsSimone Conia, Daniel Lee, Min Li, Umar Farooq Minhas, Saloni Potdar, Yunyao Li
Computational Bottlenecks of Training Small-Scale Large Language Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsSaleh Ashkboos, Iman Mirzadeh, Keivan Alizadeh, Mohammad Hossein Sekhavat, Moin Nabi, Mehrdad Farajtabar, Fartash Faghri
ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference EMNLPPublished year 2024
AuthorsRonak Pradeep, Daniel Lee, Ali Mousavi, Jeff Pound, Yisi Sang, Jimmy Lin, Ihab Ilyas, Saloni Potdar, Mostafa Arefiyan, Yunyao Li
Promoting Cross-Modal Representations to Improve Multimodal Foundation Models for Physiological Signals
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsChing Fang, Christopher Sandino, Behrooz Mahasseni, Juri Minxha, Hadi Pouransari, Erdrin Azemi, Ali Moin, Ellen Zippi
Smart Audit System Empowered by LLM
content type paper research area Speech and Natural Language Processing, research area Tools, Platforms, FrameworksPublished year 2024
AuthorsXu Yao, Xiaoxu Wu, Xi Li, Huan Xu, Chenlei Li, Ping Huang, Si Li, Xiaoning Ma, Jiulong Shan
Divide-or-Conquer? Which Part Should You Distill Your LLM?
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2024
AuthorsZhuofeng Wu, He Bai, Aonan Zhang, Jiatao Gu, VG Vinod Vydiswaran, Navdeep Jaitly, Yizhe Zhang
Combining Machine Learning and Homomorphic Encryption in the Apple Ecosystem
content type highlight research area PrivacyPublished year 2024
CtrlSynth: Controllable Image-Text Synthesis for Data-Efficient Multimodal Learning
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsQingqing Cao, Mahyar Najibi, Sachin Mehta
MUSCLE: A Model Update Strategy for Compatible LLM Evolution
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference EMNLPPublished year 2024
AuthorsJessica Echterhoff, Fartash Faghri, Raviteja Vemulapalli, Ting-Yao Hu, Chun-Liang Li, Oncel Tuzel, Hadi Pouransari
Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison
content type paper research area Data Science and Annotation, research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsJudy Hanwen Shen, Archit Sharma, Jun Qin
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
content type paper research area Methods and AlgorithmsPublished year 2024
AuthorsGaurav Patel, Chris Sandino, Behrooz Mahasseni, Ellen Zippi, Erdrin Azemi, Ali Moin, Juri Minxha
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
content type paper research area Computer Visionconference NeurIPSPublished year 2024
In collaboration with EPFL
AuthorsRoman Bachmann*, Oğuzhan Fatih Kar*, David Mizrahi*, Ali Garjani, Mingfei Gao, David Griffiths, Jiaming Hu, Afshin Dehghan, Amir Zamir
Scalable Private Search with Wally
content type paper research area PrivacyPublished year 2024
AuthorsHilal Asi, Fabian Boemer, Nicholas Genise, Muhammad Haris Mughees, Tabitha Ogilvie, Rehan Rishi, Guy N. Rothblum, Kunal Talwar, Karl Tarbe, Ruiyu Zhu, Marco Zuliani
CAMPHOR: Collaborative Agents for Multi-Input Planning and High-Order Reasoning On Device
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsYicheng Fu, Raviteja Anantha, Jianpeng Cheng
Generalizable Autoregressive Modeling of Time Series Through Functional Narratives
content type paper research area Methods and Algorithms, research area Tools, Platforms, FrameworksPublished year 2024
AuthorsRan Liu, Wenrui Ma, Ellen Zippi, Hadi Pouransari, Jingyun Xiao, Chris Sandino, Behrooz Mahasseni, Juri Minxha, Erdrin Azemi, Eva L. Dyer, Ali Moin
Progressive Entropic Optimal Transport Solvers
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsParnian Kassraie, Aram-Alexandre Pooladian, Michal Klein, James Thornton, Jonathan Niles-Weed, Marco Cuturi
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
content type paper research area Speech and Natural Language ProcessingPublished year 2024
AuthorsIman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, Mehrdad Farajtabar
Vision-Based Hand Gesture Customization from a Single Demonstration
content type paper research area Computer Vision, research area Human-Computer Interactionconference UISTPublished year 2024
AuthorsSoroush Shahi, Vimal Mollyn, Cori Tymoszek Park, Richard Kang, Asaf Liberman, Oron Levy, Jun Gong, Abdelkareem Bedri, Gierad Laput
Contrastive Localized Language-Image Pre-Training
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsHong-You Chen, Zhengfeng Lai, Haotian Zhang, Xinze Wang, Marcin Eichner, Keen You, Meng Cao, Bowen Zhang, Yinfei Yang, Zhe Gan
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
content type paper research area Computer VisionPublished year 2024
AuthorsAleksei Bochkovskii, Amaël Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R. Richter, Vladlen Koltun
On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference EMNLPPublished year 2024
AuthorsYong Lin, Skyler Seto, Maartje ter Hoeve, Katherine Metcalf, Barry-John Theobald, Xuan Wang, Yizhe Zhang, Chen Huang, Tong Zhang
When is Multicalibration Post-Processing Necessary?
content type paper research area Fairness, research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsDutch Hansen, Siddartha Devic, Preetum Nakkiran, Vatsal Sharan
Improving How Machine Translations Handle Grammatical Gender Ambiguity
content type highlight research area Speech and Natural Language ProcessingPublished year 2024
Generalizable Error Modeling for Human Data Annotation: Evidence from an Industry-Scale Search Data Annotation Program
content type paper research area Data Science and Annotationconference Journal of Data and Information QualityPublished year 2024
AuthorsHeinrich Peters, Alireza Hashemi, James Rae
Misty: UI Prototyping Through Interactive Conceptual Blending
content type paper research area Human-Computer Interaction, research area Tools, Platforms, FrameworksPublished year 2024
AuthorsYuwen Lu, Alan Leung, Amanda Swearngin, Jeffrey Nichols, Titus Barik
Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments
content type paper research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference IEEE VisualizationPublished year 2024
AuthorsAngie Boggust*, Venkatesh Sivaraman*, Yannick Assogba, Donghao Ren, Dominik Moritz, Fred Hohman
Contextualization of ASR with LLM Using Phonetic Retrieval-Based Augmentation
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsZhihong Lei, Xingyu Na, Mingbin Xu, Ernest Pusateri, Christophe Van Gysel, Yuanyuan Zhang, Shiyi Han, Zhen Huang
Automated Code Fix Suggestions for Accessibility Issues in Mobile Apps
content type paper research area Accessibility, research area Human-Computer InteractionPublished year 2024
AuthorsForough Mehralian, Titus Barik, Jeff Nichols, Amanda Swearngin
Retrieval-Augmented Correction of Named Entity Speech Recognition Errors
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsErnest Pusateri, Anmol Walia, Anirudh Kashi, Bortik Bandyopadhyay, Nadia Hyder, Sayantan Mahinder, Raviteja Anantha, Daben Liu, Sashank Gondala
Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
content type paper research area Computer Vision, research area Human-Computer Interactionconference ECCVPublished year 2024
AuthorsKeen You, Haotian Zhang, Eldon Schoop, Floris Weers, Amanda Swearngin, Jeffrey Nichols, Yinfei Yang, Zhe Gan
UI-JEPA: Towards Active Perception of User Intent Through Onscreen User Activity
content type paper research area Human-Computer Interaction, research area Methods and AlgorithmsPublished year 2024
AuthorsYicheng Fu, Raviteja Anantha, Prabal Vashisht, Jianpeng Cheng, Etai Littwin
CTRLorALTer: Conditional LoRAdapter for Efficient Zero-Shot Control & Altering of T2I Models
content type paper research area Computer Vision, research area Methods and Algorithmsconference ECCVPublished year 2024
AuthorsNick Stracke, Stefan Andreas Baumann, Josh Susskind, Miguel Angel Bautista Martin, Björn Ommer
Optimizing Byte-level Representation for End-to-End ASR
content type paper research area Speech and Natural Language Processingconference SLTPublished year 2024
AuthorsRoger Hsiao, Liuhui Deng, Erik McDermott, Ruchir Travadi, Xiaodan Zhuang
Positional Description for Numerical Normalization
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsDeepanshu Gupta, Javier Latorre
On the Benefits of Pixel-Based Hierarchical Policies for Task Generalization
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2024
AuthorsTudor Cristea-Platon, Bogdan Mazoure, Josh Susskind, Walter Talbott
Can You Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsZak Aldeneh, Takuya Higuchi, Jee-weon Jung, Skyler Seto, Tatiana Likhomanenko, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe
Novel-View Acoustic Synthesis From 3D Reconstructed Rooms
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsByeongjoo Ahn, Karren Yang, Brian Hamilton, Jonathan Sheaffer, Anurag Ranjan, Miguel Sarabia del Castillo, Oncel Tuzel, Rick Chang
ReALM: Reference Resolution as Language Modeling
content type paper research area Speech and Natural Language Processingconference SIGDIALPublished year 2024
AuthorsJoel Moniz, Soundarya Krishnan, Melis Ozyildirim, Prathamesh Saraf, Halim Cagri Ates, Yuan Zhang, Hong Yu
RepCNN: Micro-Sized, Mighty Models for Wakeword Detection
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsArnav Kundu, Prateeth Nayak, Priyanka Padmanabhan, Devang Naik
APE: Active Prompt Engineering - Identifying Informative Few-Shot Examples for LLMs
content type paper research area Speech and Natural Language Processing, research area Tools, Platforms, Frameworksconference NAACLPublished year 2024
AuthorsKun Qian, Farima Fatahi Bayat, Anton Belyi, Yash Govind, Rahul Khot, Katherine Luna, Azadeh Nikfarjam, Xiaoguang Qi, Yisi Sang, Fei Wu, Victor (AIML) Zhang, Yunyao Li, Samira Khorshidi, Xianqi Chu
AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ECCVPublished year 2024
AuthorsAndrew Rouditchenko, Ronan Collobert, Tatiana Likhomanenko
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
content type paper research area Speech and Natural Language Processing, research area Tools, Platforms, FrameworksPublished year 2024
AuthorsJiarui Lu, Thomas Holleis, Yizhe Zhang, Bernhard Aumayer, Feng Nan, Felix Bai, Shuang Ma, Shen Ma, Mengyu Li, Guoli Yin, Zirui Wang, Ruoming Pang
Generating Gender Alternatives in Machine Translation
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsSarthak Garg, Mozhdeh Gheini, Clara Emmanuel, Tatiana Likhomanenko, Qin Gao, Matthias Paulik
KGLens: Towards Efficient and Effective Knowledge Probing of Large Language Models with Knowledge Graphs
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsDaniel Zheng, Richard Bai, Yizhe Zhang, Yi (Siri) Su, Xiaochuan Niu, Navdeep Jaitly
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsPratyush Maini, Skyler Seto, Richard Bai, David Grangier, Yizhe Zhang, Navdeep Jaitly
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsAiwei Liu, Haoping Bai, Zhiyun Lu, Xiang Kong, Simon Wang, Jiulong Shan, Meng Cao, Lijie Wen
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsKeivan Alizadeh, Iman Mirzadeh, Dmitry Belenko, S. Karen Khatamifard, Minsik Cho, Carlo C Del Mundo, Mohammad Rastegari, Mehrdad Farajtabar
BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks
content type paper research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)Published year 2024
AuthorsRuijia Cheng, Titus Barik, Alan Leung, Fred Hohman, Jeffrey Nichols
ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsRonak Pradeep, Daniel Lee, Ali Mousavi, Jeff Pound, Yisi Sang, Jimmy Lin, Ihab Ilyas, Saloni Potdar, Mostafa Arefiyan Khalilabad, Yunyao Li
Model-Driven Heart Rate Estimation and Heart Murmur Detection Based on Phonocardiogram
content type paper research area Data Science and Annotation, research area HealthPublished year 2024
AuthorsJingping Nie, Ran Liu, Behrooz Mahasseni, Erdrin Azemi, Vikramjit Mitra
Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsZhuoyuan Mao, Yen Yu
Apple Intelligence Foundation Language Models
content type paperPublished year 2024
DataComp-LM: In Search of the Next Generation of Training Sets for Language Models
content type paper research area Data Science and Annotation, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsJeffrey Li, Alex Fang, Hadi Pour Ansari, Fartash Faghri, Alaaeldin Mohamed Elnouby Ali, Alexander Toshev, Vaishaal Shankar, Georgios Smyrnis, Matt Jordan, Maor Igvi, Alex Dimakis, Hanlin Zhang, Hritik Bansal, Igor Vasiljevic, Jean Mercat, Jenia Jitsev, Kushal Arora, Mayee Chen, Niklas Muenninghoff, Luca Soldaini, Pang Wei Koh, Reinhard Heckel, Rui Xin, Samir Gadre, Rulin Shao, Sarah Pratt, Saurabh Garg, Sedrick Keh, Suchin Gururangan, Sunny Sanyal, Yonatan Bitton, Thomas Kollar, Mitchell Wortsman, Etash Guha, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Joshua Gardner, Marianna Nezhurina, Achal Dave, Yair Carmon, Ludwig Schmidt
Instruction-Following Speech Recognition
content type paper research area Speech and Natural Language Processingconference NeurIPSPublished year 2024
AuthorsCheng-I Jeff Lai, Zhiyun Lu, Liangliang Cao, Ruoming Pang
LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICMLPublished year 2024
AuthorsQichen Fu, Minsik Cho, Thomas Merth, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi
Pre-Trained Foundation Model Representations to Uncover Breathing Patterns in Speech
content type paper research area Health, research area Speech and Natural Language Processingconference KDDPublished year 2024
AuthorsVikramjit Mitra, Anirban Chatterjee, Ke Zhai, Helen Weng, Ayuko Hill, Nicole Hay, Christopher Webb, Jamie Cheng, Erdrin Azemi
Federated Learning With Differential Privacy for End-to-End Speech Recognition
content type paper research area Privacy, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsMartin Pelikan∗, Sheikh Shams Azam, Vitaly Feldman, Jan “Honza” Silovsky, Kunal Talwar, Tatiana Likhomanenko∗
Instance Optimal Private Density Estimation in the Wasserstein Distance
content type paper research area Privacyconference TPDPPublished year 2024
AuthorsVitaly Feldman, Audra McMillan, Satchit Sivakumar, Kunal Talwar
Samplable Anonymous Aggregation for Private Federated Data Analytics
content type paper research area Privacy, research area Tools, Platforms, FrameworksPublished year 2024
AuthorsKunal Talwar, Shan Wang, Audra McMillan, Vojta Jina, Vitaly Feldman, Pansy Bansal, Bailey Basile, Aine Cahill, Yi Sheng Chan, Mike Chatzidakis, Junye Chen, Oliver Chick, Mona Chitnis, Suman Ganta, Yusuf Goren, Filip Granqvist, Kristine Guo, Frederic Jacobs, Omid Javidbakht, Albert Liu, Richard Low, Dan Mascenik, Steve Myers, David Park, Wonhee Park, Gianni Parsa, Tommy Pauly, Christian Priebe, Rehan Rishi, Guy Rothblum, Michael Scaria, Linmao Song, Congzheng Song, Karl Tarbe, Sebastian Vogt, Luke Winstrom, Shundong Zhou
Improving GFlowNets for Text-to-Image Diffusion Alignment
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at ICMLPublished year 2024
AuthorsDinghuai Zhang, Yizhe Zhang, Jiatao Gu, Ruixiang Zhang, Josh Susskind, Navdeep Jaitly, Shuangfei Zhai
PINE: Efficient Norm-Bound Verification for Secret-Shared Vectors
content type paper research area Methods and Algorithms, research area Privacyconference USENIX SecurityPublished year 2024
AuthorsGuy N. Rothblum, Eran Omri, Junye Chen, Kunal Talwar
Projected Language Models: A Large Model Pre-Segmented Into Smaller Ones
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at ICMLPublished year 2024
AuthorsDavid Grangier, Angelos Katharopoulos, Pierre Ablin, Awni Hannun
Towards Automated Accessibility Report Generation for Mobile Apps
content type paper research area Accessibility, research area Human-Computer Interactionconference ACM Transactions on Computer-Human InteractionPublished year 2024
AuthorsAmanda Swearngin, Jason Wu, Xiaoyi Zhang, Esteban Gomez, Jen Coughenour, Rachel Stukenborg, Bhavya Garg, Greg Hughes, Adriana Hilliard, Jeffrey P. Bigham, Jeffrey Nichols
Ferretv2: An Improved Baseline for Referring and Grounding
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference COLMPublished year 2024
AuthorsHaotian Zhang, Haoxuan You, Philipp Dufter, Bowen Zhang, Chen Chen, Hong-You Chen, Tsu-Jui Fu, William Yang Wang, Shih-Fu Chang, Zhe Gan, Yinfei Yang
On a Neural Implementation of Brenier's Polar Factorization
content type paper research area Methods and Algorithmsconference ICMLPublished year 2024
AuthorsNina Vesseron, Marco Cuturi Cameto
A Direct Algorithm for Multi-Gyroscope Infield Calibration
content type paper research area Computer Vision, research area Methods and Algorithmsconference IROSPublished year 2024
AuthorsTianheng Wang, Stergios Roumeliotis
CodeAct: Your LLM Agent Acts Better when Generating Code
content type paper research area Speech and Natural Language Processingconference ICMLPublished year 2024
AuthorsXingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Ji Heng
Contrasting Multiple Representations with the Multi-Marginal Matching Gap
content type paper research area Methods and Algorithmsconference ICMLPublished year 2024
AuthorsZoe Piran, Michal Klein, James Thornton, Marco Cuturi Cameto
How Smooth Is Attention?
content type paper research area Methods and Algorithmsconference ICMLPublished year 2024
AuthorsValérie Castin, Pierre Ablin, Gabriel Peyré
On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions
content type paper research area Methods and Algorithmsconference ICMLPublished year 2024
AuthorsDenys Pushkin, Raphael Berthier, Emmanuel Abbe
Revealing the Utilized Rank of Subspaces of Learning in Neural Networks
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at ICMLPublished year 2024
AuthorsIsha Garg, Christian Koguchi, Eshan Verma, Daniel Ulbricht
Whispering Experts: Toxicity Mitigation in Pre-trained Language Models by Dampening Expert Neurons
content type paper research area Fairness, research area Speech and Natural Language Processingconference ICMLPublished year 2024
AuthorsXavier Suau Cuadros, Pieter Delobelle, Rin Metcalf Susa, Armand Joulin, Nick Apostoloff, Luca Zappella, Pau Rodriguez Lopez
Careful With That Scalpel: Improving Gradient Surgery With an EMA
content type paper research area Methods and Algorithmsconference ICMLPublished year 2024
AuthorsYu-Guan Hsieh, James Thornton, Eugene Ndiaye, Michal Klein, Marco Cuturi Cameto, Pierre Ablin
Enhancing CTC-based Speech Recognition with Diverse Modeling Units
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsMichael Han, Zhihong Lei, Mingbin Xu, Xingyu Na, Zhen Huang
Omnipredictors for Regression and the Approximate Rank of Convex Functions
content type paper research area Fairness, research area Methods and Algorithmsconference COLTPublished year 2024
AuthorsParikshit Gopalan, Princewill Okoroafor, Prasad Raghavendra, Abhishek Shetty, Mihir A Singhal
On Computationally Efficient Multi-Class Calibration
content type paper research area Fairness, research area Methods and Algorithmsconference COLTPublished year 2024
AuthorsParikshit Gopalan, Lunjia Hu, Guy Rothblum
Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICMLPublished year 2024
AuthorsThomas Merth, Qichen Fu, Mohammad Rastegari, Mahyar Najibikohnehshahri
Accurate Knowledge Distillation via N-best Reranking
content type paper research area Speech and Natural Language Processingconference NAACLPublished year 2024
AuthorsHendra Setiawan
TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsYinhong Liu, Yimai Fang, David Vandyke, Nigel Collier
Transfer Learning for Structured Pruning under Limited Task Data
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsLucio Dery, David Grangier, Awni Hannun
Bytes Are All You Need: Transformers Operating Directly On File Bytes
content type paper research area Computer Vision, research area Methods and AlgorithmsTransactions on Machine Learning Research (TMLR)Published year 2024
AuthorsMax Horton, Sachin Mehta, Ali Farhadi, Mohammad Rastegari
MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsYusu Qian, Hanrong Ye, Jean-Philippe Fauconnier Biard, Peter Grasch, Yinfei Yang, Zhe Gan
Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages
content type paper research area Methods and Algorithms, research area Privacyconference ICMLPublished year 2024
AuthorsHilal Asi, Vitaly Feldman, Jelani Nelson, Huy Nguyen, Kunal Talwar, Samson Zhou
Applying RLAIF for Code Generation with API-usage in Lightweight LLMs
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at ACLPublished year 2024
AuthorsSujan Dutta, Sayantan Mahinder, Raviteja Anantha, Bortik Bandyopadhyay
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
content type paper research area Methods and AlgorithmsPublished year 2024
AuthorsEmmanuel Abbe, Samy Bengio, Aryo Lotfi, Colin Sandon, Omid Saremi
Optimization Without Retraction on the Random Generalized Stiefel Manifold
content type paper research area Methods and Algorithmsconference ICMLPublished year 2024
AuthorsSimon Vary, Pierre Ablin, Bin Gao, P.-A. Absil
Revisiting Non-separable Binary Classification and its Applications in Anomaly Detection
content type paper research area Methods and AlgorithmsTransactions on Machine Learning Research (TMLR)Published year 2024
AuthorsMatthew Lau, Ismaila Seck, Athanasios Meliopoulos, Wenke Lee, Eugene Ndiaye
Toward Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsAkchay Srivastava, Atif Memon
Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World Effectiveness
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsSatyam Kumar, Sai Srujana Buddi, Utkarsh Oggy Sarawgi, Vineet Garg, Shivesh Ranjan, Ognjen (Oggi) Rudovic, Ahmed Hussen Abdelaziz, Saurabh Adya
Conformer-Based Speech Recognition on Extreme Edge-Computing Devices
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference NAACLPublished year 2024
AuthorsMingbin Xu, Alex Jin, Sicheng Wang, Mu Su, Tim Ng, Henry Mason, Michael Han, Zhihong Lei, Yaqiao Deng, Zhen Huang, Mahesh Krishnamoorthy
Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsShruti Palaskar, Oggi Rudovic, Sameer Dharur, Florian Pesce, Gautam Krishna, Aswin Sivaraman, Jack Berkowitz, Ahmed Hussen Abdelaziz, Saurabh Adya, Ahmed Tewfik
Synthetic Query Generation using Large Language Models for Virtual Assistants
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference SIGIRPublished year 2024
AuthorsSonal Sannigrahi, Thiago Fraga da Silva, Youssef Oualil, Christophe Van Gysel
ESPnet-SPK: Full Pipeline Speaker Verification Toolkit with Multiple Reproducible Recipes, Self-Supervised Front-Ends, and Off-the-Shelf Models
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsJee-weon Jung, Wangyou Zhang, Jiatong Shi, Zak Aldeneh, Takuya Higuchi, Barry Theobald, Ahmed Hussen Abdelaziz, Shinji Watanabe
Hypernetworks for Personalizing ASR to Atypical Speech
content type paper research area Accessibility, research area Speech and Natural Language Processingconference Transactions of the Association for Computational LinguisticsPublished year 2024
AuthorsMax Müller-Eberstein*, Dianna Yee*, Karren Yang, Gautam Varma Mantena, Colin Lea
On-Device Query Auto-Completion for Email Search
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference ECIRPublished year 2024
AuthorsYifan Qiao, Otto Godwin, Hua Ouyang
Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistants
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference International Journal of Speech TechnologyPublished year 2024
AuthorsDarien Zhang, Sashank Gondala, Thiago Fraga da Silva, Christophe Van Gysel
Time Sensitive Knowledge Editing through Efficient Finetuning
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsHugh Ge, Ali Mousavi, Edouard Grave, Armand Joulin, Kun Qian, Benjamin Han, Mostafa Arefiyan Khalilabad, Yunyao Li
Transformer-based Model for ASR N-Best Rescoring and Rewriting
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2024
AuthorsEdwin Kang, Christophe Van Gysel, Man-Hung Siu
Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation
content type paper research area Data Science and Annotation, research area Speech and Natural Language Processingconference LREC-COLINGPublished year 2024
AuthorsMatthias Sperber, Ondřej Bojar, Barry Haddow, Dávid Javorský, Xutai Ma, Matteo Negri, Jan Niehues, Peter Polák, Elizabeth Salesky, Katsuhito Sudoh, Marco Turchi
Improved Modelling of Federated Datasets using Mixtures-of-Dirichlet-Multinomials
content type paper research area Data Science and Annotation, research area Methods and Algorithmsconference ICMLPublished year 2024
AuthorsJonathan Scott, Áine Cahill
Introducing Apple’s On-Device and Server Foundation Models
content type highlightPublished year 2024
AGRaME: Any Granularity Ranking with Multi-Vector Embeddings
content type paper research area Knowledge Bases and Search, research area Methods and AlgorithmsPublished year 2024
AuthorsRevanth Gangi Reddy, Omar Attia, Yunyao Li, Heng Ji, Saloni Potdar
Entity Disambiguation via Fusion Entity Decoding
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference NAACLPublished year 2024
AuthorsJunxiong Wang, Ali Mousavi, Omar Attia, Ronak Pradeep, Saloni Potdar, Alexander M. Rush, Umar Farooq Minhas, Yunyao Li
Embedding Pose Graph, Enabling 3D Foundation Model Capabilities with a Compact Representation
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2024
AuthorsHugues Thomas, Jian Zhang
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingTransactions on Machine Learning Research (TMLR)Published year 2024
AuthorsMohammadreza Salehi, Mehrdad Farajtabar, Maxwell Horton, Fartash Faghri, Hadi Pouransari, Raviteja Vemulapalli, Oncel Tuzel, Ali Farhadi, Mohammad Rastegari, Sachin Mehta
Affine-based Deformable Attention and Selective Fusion for Semi-dense Matching
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at CVPRPublished year 2024
AuthorsHongkai Chen, Zixin Luo, Ray Tian, Xuyang Bai, Aron Wang, Lei Zhou, Mingmin Zhen, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan
Efficient Diffusion Models without Attention
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2024
AuthorsJing Nathan Yan, Jiatao Gu, Alexander M. Rush
KPConvX: Modernizing Kernel Point Convolution with Kernel Attention
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2024
AuthorsHugues Thomas, Hubert Tsai, Timothy D. Barfoot, Jian Zhang
ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
content type paper research area Computer Visionconference NeurIPSPublished year 2024
AuthorsJingYuan Zhu, Shiyu Li, Andy Liu, Ping Huang, Jiulong Shan, Huimin Ma, Jian Yuan
Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference CVPRPublished year 2024
AuthorsKarren Yang, Anurag Ranjan, Rick Chang, Raviteja Vemulapalli, Oncel Tuzel
Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
content type paper research area Methods and Algorithmsconference ICMLPublished year 2024
AuthorsYuyang Wang, Ahmed Elhag, Navdeep Jaitly, Josh Susskind, Miguel Angel Bautista Martin
On Efficient and Statistical Quality Estimation for Data Annotation
content type paper research area Data Science and Annotationconference ACLPublished year 2024
AuthorsJan-Christoph Klie, Juan Haladjian, Marc Kirchner, Rahul Nair
Automatic Creative Selection with Cross-Modal Matching
content type paper research area Computer Vision, research area Knowledge Bases and Searchconference BayLearnPublished year 2024
AuthorsAlex Kim, Jia Huang, Rob Monarch, Jerry Kwac, Anikesh Kamath, Parmeshwar (Parry) Khurd, Kailash Thiyagarajan, Goodman Gu
ContextQ: Generated Questions to Support Meaningful Parent-Child Dialogue While Co-Reading
content type paper research area Human-Computer Interactionconference ACM Interaction Design and ChildrenPublished year 2024
AuthorsGriffin Dietz Smith, Siddhartha Prasad, Matt J. Davidson, Leah Findlater, R. Benjamin Shapiro
KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICMLPublished year 2024
AuthorsMinsik Cho, Mohammad Rastegari, Devang Naik
pfl-research: Simulation Framework for Accelerating Research in Private Federated Learning
content type paper research area Privacy, research area Tools, Platforms, FrameworksPublished year 2024
AuthorsFilip Granqvist, Congzheng Song, Aine Cahill, Rogier van Dalen, Martin Pelikan, Yi Sheng Chan, Xiaojun Feng, Natarajan Krishnaswami, Vojta Jina, Mona Chitnis
Generative Modeling with Phase Stochastic Bridges
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsTianrong Chen, Jiatao Gu, Laurent Dinh, Evangelos A. Theodorou, Joshua Susskind, Shuangfei Zhai
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at ICLRPublished year 2024
AuthorsPratyush Maini, Skyler Seto, He Bai, David Grangier, Yizhe Zhang, Navdeep Jaitly
Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
content type paper research area Computer Visionconference ICMLPublished year 2024
AuthorsRaviteja Vemulapalli, Hadi Pouransari, Fartash Faghri, Sachin Mehta, Mehrdad Farajtabar, Mohammad Rastegari, Oncel Tuzel
Conformal Prediction via Regression-as-Classification
content type paper research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsEtash Guha, Shlok Natarajan, Thomas Mollenhoff, Emtiyaz Khan, Eugene Ndiaye
Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
content type paper research area Data Science and Annotation, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsAadi Saha, Brano Kveton
Guiding Instruction-based Image Editing via Multimodal Large Language Models
content type paper research area Computer Visionconference ICLRPublished year 2024
AuthorsTsu-Jui Fu, Wenze Hu, Xianzhi Du, William Wang, Yinfei Yang, Zhe Gan
Posterior Uncertainty Quantification in Neural Networks using Data Augmentation
content type paper research area Methods and Algorithmsconference AISTATSPublished year 2024
AuthorsLuhuan Wu, Sinead Williamson
Pseudo-Generalized Dynamic View Synthesis from a Video
content type paper research area Computer Visionconference ICLRPublished year 2024
AuthorsXiaoming Zhao, Alex Colburn, Fangchang Ma, Miguel Angel Bautista Martin, Josh Susskind, Alex Schwing
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICLRPublished year 2024
AuthorsIman Mirzadeh, Keivan Alizadeh Vahid, Sachin Mehta, Carlo C Del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, Mehrdad Farajtabar
Compressing LLMs: The Truth is Rarely Pure and Never Simple
content type paper research area Speech and Natural Language Processingconference ICLRPublished year 2024
AuthorsAjay Jaiswal, Zhe Gan, Xianzhi Du, Bowen Zhang, Zhangyang Wang, Yinfei Yang
How Far Are We from Intelligent Visual Deductive Reasoning?
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingHow Far Are We from AGI?Published year 2024
AuthorsYizhe Zhang, He Bai, Ruixiang Zhang, Jiatao Gu, Shuangfei Zhai, Josh Susskind, Navdeep Jaitly
Large Language Models as Generalizable Policies for Embodied Tasks
content type paper research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsAndrew Szot, Max Schwarzer, Harsh Agrawal, Bogdan Mazoure, Walter Talbott, Rin Metcalf Susa, Natalie Mackraz, Devon Hjelm, Alexander Toshev
Manifold Diffusion Fields
content type paper research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsAhmed Elhag, Yuyang Wang, Josh Susskind, Miguel Angel Bautista Martin
MOFI: Learning Image Representation from Noisy Entity Annotated Images
content type paper research area Computer Visionconference ICLRPublished year 2024
AuthorsWentao Wu, Aleksei Timofeev, Chen Chen, Bowen Zhang, Kun Duan, Shuangning Liu, Yantao Zheng, Jonathan Shlens, Xianzhi Du, Zhe Gan, Yinfei Yang
Poly-View Contrastive Learning
content type paper research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsAmitis Shidani, Devon Hjelm, Jason Ramapuram, Russ Webb, Eeshan Gunesh Dhekane, Dan Busbridge
When Can Transformers Reason With Abstract Symbols?
content type paper research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsEnric Boix-Adsera, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Josh Susskind
Direct2.5: Diverse 3D Content Creation via Multi-view 2.5D Diffusion
content type paper research area Computer Visionconference CVPRPublished year 2024
AuthorsYuanxun Lu, Jingyang Zhang, Shiwei Li, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan, Xun Cao, Yao Yao
JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling
content type paper research area Computer Visionconference ICLRPublished year 2024
AuthorsJingyang Zhang, Shiwei Li, Yuanxun Lu, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan, Yao Yao
Label-Efficient Sleep Staging Using Transformers Pre-trained with Position Prediction
content type paper research area Health, research area Methods and AlgorithmsIEEE Conference on Artificial Intelligence for Medicine, Health, and CarePublished year 2024
AuthorsSayeri Lala, Hanlin Goh, Chris Sandino
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7× Faster Pre-training on Web-scale Image-Text Data
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2024
AuthorsSachin Mehta, Max Horton, Fartash Faghri, Mohammad Sekhavat, Mahyar Najibikohnehshahri, Mehrdad Farajtabar, Oncel Tuzel, Mohammad Rastegari
HumMUSS: Human Motion Understanding using State Space Models
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2024
AuthorsArnab Mondal, Stefano Alletto, Denis Tome'
Matryoshka Diffusion Models
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsJiatao Gu, Shuangfei Zhai, Yizhe Zhang, Josh Susskind, Navdeep Jaitly
OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
content type paper research area Speech and Natural Language ProcessingWorkshop at ICMLPublished year 2024
AuthorsSachin Mehta, Mohammad Sekhavat, Qingqing Cao, Max Horton, Yanzi Jin, Frank Sun, Iman Mirzadeh, Mahyar Najibikohnehshahri, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari
Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference
content type paper research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference CHIPublished year 2024
AuthorsFred Hohman, Chaoqun Wang, Jinmook Lee, Jochen Görtler, Dominik Moritz, Jeffrey Bigham, Zhile Ren, Cecile Foret, Qi Shan, Xiaoyi Zhang
Think While You Write Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference NAACLPublished year 2024
AuthorsYifu Qiu, Varun Embar, Shay B. Cohen, Benjamin Han
The Slingshot Effect: A Late-Stage Optimization Anomaly in Adam-Family of Optimization Methods
content type paper research area Computer Vision, research area Methods and AlgorithmsTransactions on Machine Learning Research (TMLR)Published year 2024
AuthorsVimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua M. Susskind
Hindsight PRIORs for Reward Learning from Human Preferences
content type paper research area Human-Computer Interaction, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsMudit Verma, Rin Metcalf Susa
FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descen
content type paper research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsZiyao Wang, Jianyu Wang, Ang Li
Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals
content type paper research area Health, research area Methods and AlgorithmsWorkshop at ICLRPublished year 2024
AuthorsRan Liu, Ellen Zippi, Hadi Pour Ansari, Chris Sandino, Jingping Nie, Hanlin Goh, Erdrin Azemi, Ali Moin
Hierarchical and Dynamic Prompt Compression for Efficient Zero-shot API Usage
content type paper research area Speech and Natural Language Processingconference EACLPublished year 2024
AuthorsYichen Jiang, Marco Del Vecchio, Anders Johannsen, Mohit Bansal
Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsYuhang Zang, Hanlin Goh, Josh Susskind, Chen Huang
Vanishing Gradients in Reinforcement Finetuning of Language Models
content type paper research area Speech and Natural Language Processingconference ICLRPublished year 2024
AuthorsNoam Razin, Hattie Zhou, Preetum Nakkilan, Josh Susskind, Omid Saremi, Arwen Bradley, Vimal Thilak, Etai Littwin
Data Filtering Networks
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsAlex Fang, Albin Madappally Jose, Amit Jain, Ludwig Schmidt, Alexander Toshev, Vaishaal Shankar
Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences
content type paper research area Human-Computer Interaction, research area Methods and Algorithmsconference CHIPublished year 2024
AuthorsFred Hohman, Mary Beth Kery, Donghao Ren, Dominik Moritz
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2024
AuthorsPavan Kumar Anasosalu Vasu*, Hadi Pour Ansari*, Fartash Faghri*, Raviteja Vemulapalli, Oncel Tuzel
Streaming Anchor Loss: Augmenting Supervision with Temporal Significance
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICASSPPublished year 2024
AuthorsOggy Sarawgi, Jack Berkowitz, Vineet Garg, Arnav Kundu, Minsik Cho, Sai Srujana Buddi, Saurabh Adya, Ahmed Tewfik
Towards a World-English Language Model
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2024
AuthorsRricha Jalota, Lyan Verwimp, Markus Nussbaum-Thom, Amr Mousa, Arturo Argueta, Youssef Oualil
Efficient-3Dim: Learning a Generalizable Single Image Novel View Synthesizer in One Day
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsYifan Jiang, Hao Tang, Rick Chang, Liangchen Song, Zhangyang Wang, Liangliang Cao
A Multi-signal Large Language Model for Device-directed Speech Detection
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2024
AuthorsDominik Wagner, Alex Churchill, Siddharth Sigtia, Panos Georgiou, Matt Mirsamadi, Aarshee Mishra, Erik Marchi
TiC-CLIP: Continual Training of CLIP Models
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsSaurabh Garg, Hadi Pour Ansari, Mehrdad Farajtabar, Sachin Mehta, Raviteja Vemulapalli, Oncel Tuzel, Vaishaal Shankar, Fartash Faghri
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsBrandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier Biard, Sam Dodge, Philipp Dufter, Bowen Zhang, Dhruti Shah, Xianzhi Du, Futang Peng, Haotian Zhang, Floris Weers, Anton Belyi, Karanjeet Singh, Doug Kang, Ankur Jain, Hongyu He, Max Schwarzer, Tom Gunter, Xiang Kong, Aonan Zhang, Jianyu Wang, Chong Wang, Nan Du, Tao Lei, Sam Wiseman, Mark Lee, Zirui Wang, Ruoming Pang, Peter Grasch, Alexander Toshev, Yinfei Yang
Enhancing Paragraph Generation with a Latent Language Diffusion Model
content type highlight research area Methods and AlgorithmsPublished year 2024
Construction of Paired Knowledge Graph - Text Datasets Informed by Cyclic Evaluation
content type paper research area Knowledge Bases and Searchconference LREC-COLINGPublished year 2024
AuthorsAli Mousavi, Xin Zhan, Richard Bai, Peng Shi, Theo Rekatsinas, Benjamin Han, Yunyao Li, Jeff Pound, , Josh Susskind, Natalie Schluter, Ihab Ilyas, Navdeep Jaitly
Personalizing Health and Fitness with Hybrid Modeling
content type highlight research area Health, research area Methods and AlgorithmsPublished year 2024
CEASE: Conversation Embeddings for Implicit Summarisation in the Continuous Space
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference NAACLPublished year 2024
AuthorsSeanie Lee, Alex Coca, Jianpeng Cheng, Anders Johannsen, Joris Driesen
Corpus Synthesis for Zero-shot ASR Domain Adaptation using Large Language Models
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2024
AuthorsHsuan Su, Ting-Yao Hu, Hema Swetha Koppula, Raviteja Vemulapalli, Jen-Hao Rick Chang, Karren Yang, Gautam Varma Mantena, Oncel Tuzel
MotionPrint: Ready-to-Use, Device-Agnostic, and Location-Invariant Motion Activity Models
content type paper research area Human-Computer InteractionPublished year 2024
AuthorsRebecca Adaimi, Abdelkareem Bedri, Jun Gong, Richard Kang, Joanna Arreaza-Taylor, Gerri-Michelle Pascual, Michael Ralph, Gierad Laput
Randomized Algorithms for Precise Measurement of Differentially-private, Personalized Recommendations
content type paper research area PrivacyWorkshop at AAAIPublished year 2024
AuthorsAllegra Laro, Yanqing Chen, Hao He, Babak Aghazadeh
VeCLIP: Improving CLIP Training via Visual-enriched Captions
content type paper research area Computer Visionconference ECCVPublished year 2024
AuthorsJeff Lai*, Haotian Zhang*, Bowen Zhang, Wentao Wu, Felix Bai, Aleksei Timofeev, Xianzhi Du, Zhe Gan, Jiulong Shan, Chen-Nee Chuah, Yinfei Yang, Meng Cao
AXNav: Replaying Accessibility Tests from Natural Language
content type paper research area Accessibility, research area Human-Computer Interactionconference CHIPublished year 2024
AuthorsMaryam Taeb, Amanda Swearngin, Eldon Schoop, Regina Cheng, Yue Jiang, Jeff Nichols
Merge Vision Foundation Models via Multi-Task Distillation
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2024
AuthorsHaoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel, Hadi Pour Ansari
Moonwalk: Advancing Gait-Based User Recognition on Wearable Devices with Metric Learning
content type paper research area Human-Computer Interaction, research area PrivacyPublished year 2024
AuthorsAsaf Liberman*, Oron Levy*, Soroush Shahi, Cori Tymoszek Park, Mike Ralph, Richard Kang, Abdelkareem Bedri, Gierad Laput
Vision-Based Hand Gesture Customization from a Single Demonstration
content type paper research area Computer Vision, research area Human-Computer InteractionPublished year 2024
AuthorsSoroush Shahi, Cori Tymoszek Park, Richard Kang, Asaf Liberman, Oron Levy, Jun Gong, Abdelkareem Bedri, Gierad Laput
Humanizing Word Error Rate for ASR Transcript Readability and Accessibility
content type highlight research area Data Science and Annotation, research area Speech and Natural Language ProcessingPublished year 2024
Human Following in Mobile Platforms with Person Re-Identification
content type paper research area Methods and Algorithmsconference CASEPublished year 2024
AuthorsMario Srouji, Jian Zhang, Hugues Thomas
Privacy-Preserving Quantile Treatment Effect Estimation for Randomized Controlled Trials
content type paper research area Data Science and Annotationconference CODEPublished year 2024
AuthorsLeon Yao, Paul Yiming Li, Jiannan Lu
SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking
content type paper research area Data Science and Annotation, research area Speech and Natural Language Processingconference EACLPublished year 2024
AuthorsAtharva Kulkarni, Andy Tseng, Joel Moniz, Dhivya Piraviperumal, Hong Yu, Shruti Bhargava
What Can CLIP Learn From Task-specific Experts?
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2024
AuthorsReza Salehi, Mehrdad Farajtabar, Max Horton, Fartash Faghri, Hadi Pour Ansari, Raviteja Vemulapalli, Oncel Tuzel, Ali Farhadi, Mohammad Rastegari, Sachin Mehta
Multichannel Voice Trigger Detection Based on Transform-average-concatenate
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2024
AuthorsTakuya Higuchi, Avamarie Brueggeman, Masood Delfarah, Stephen Shum
Keyframer: Empowering Animation Design using Large Language Models
content type paper research area Human-Computer Interaction, research area Tools, Platforms, FrameworksPublished year 2024
AuthorsTiffany Tseng, Ruijia Cheng, Jeffrey Nichols
Resource-constrained Stereo Singing Voice Cancellation
content type paper research area Methods and Algorithmsconference ICASSPPublished year 2024
AuthorsClara Borrelli, James Rae, Dogac Basaran, Matt McVicar, Mehrez Souden, Matthias Mauch
Efficient ConvBN Blocks for Transfer Learning and Beyond
content type paper research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsKaichao You, Guo Qin, Anchang Bao, Meng Cao, Ping Huang, Jiulong Shan, Mingsheng Long
The Entity-Deduction Arena: A Playground for Probing the Conversational Reasoning and Planning Capabilities of LLMs
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ACLPublished year 2024
AuthorsYizhe Zhang, Jiarui Lu, Navdeep Jaitly
Differentially Private Heavy Hitter Detection using Federated Analytics
content type paper research area Methods and Algorithms, research area Privacyconference ICML, conference IEEE SaTMLPublished year 2024
In collaboration with Stanford University
AuthorsKaran Chadha, Junye Chen, John Duchi, Vitaly Feldman, Hanieh Hashemi, Omid Javidbakht, Audra McMillan, and Kunal Talwar
Scalable Pre-training of Large Autoregressive Image Models
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2024
AuthorsAlaaeldin El-Nouby, Michal Klein, Shuangfei Zhai, Miguel Angel Bautista, Alexander Toshev, Vaishaal Shankar, Joshua M Susskind, Armand Joulin
Acoustic Model Fusion for End-to-end Speech Recognition
content type paper research area Speech and Natural Language Processingconference ASRUPublished year 2024
AuthorsZhihong Lei, Mingbin Xu, Shiyi Han, Leo Liu, Zhen Huang, Tim Ng, Yuanyuan Zhang, Ernest Pusateri, Mirko Hannemann, Yaqiao Deng, Man-Hung Siu
Co-ML: Collaborative Machine Learning Model Building for Developing Dataset Design Practices
content type paper research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference ACM TOCEPublished year 2024
AuthorsTiffany Tseng, Matt J. Davidson, Luis Morales-Navarro, Jennifer King Chen, Victoria Delaney, Mark Leibowitz, Jazbo Beason, R. Benjamin Shapiro
Flexible Keyword Spotting based on Homogeneous Audio-Text Embedding
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2024
AuthorsKumari Nishu, Minsik Cho, Paul Dixon, Devang Naik
Investigating Salient Representations and Label Variance Modeling in Dimensional Speech Emotion Analysis
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICASSPPublished year 2024
AuthorsVikramjit Mitra, Jingping Nie, Erdrin Azemi
Large-scale Training of Foundation Models for Wearable Biosignals
content type paper research area Health, research area Methods and Algorithmsconference ICLRPublished year 2024
AuthorsSalar Abbaspourazad, Oussama Elachqar, Andrew C. Miller, Saba Emrani, Udhyakumar Nallasamy, Ian Shapiro
User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates
content type paper research area Methods and Algorithms, research area Privacyconference AISTATSPublished year 2024
AuthorsHilal Asi, Daogao Liu
Bin Prediction for Better Conformal Prediction
content type paper research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2024
AuthorsEtash Guha, Shlok Natarajan, Thomas Möllenhoff, Emtiyaz Khan, Eugene Ndiaye
FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline
content type paper research area Computer Vision, research area Methods and Algorithmsconference WACVPublished year 2024
AuthorsChien-Yu Lin, Qichen Fu, Thomas Merth, Karren Yang, Anurag Ranjan
Hybrid Model Learning for Cardiovascular Biomarkers Inference
content type paper research area Health, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2024
AuthorsOrtal Senouf, Jens Behrmann, Joern-Henrik Jacobsen, Pascal Frossard, Emmanuel Abbe, Antoine Wehenkel
Improving Vision-inspired Keyword Spotting Using a Streaming Conformer Encoder With Input-dependent Dynamic Depth
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICASSPPublished year 2024
AuthorsAlexandre Bittar, Paul Dixon, Mohammad Samragh, Kumari Nishu, Devang Naik
Simulation-based Inference for Cardiovascular Models
content type paper research area Methods and Algorithms, research area Tools, Platforms, FrameworksWorkshop at NeurIPSPublished year 2024
AuthorsAntoine Wehenkel, Jens Behrmann, Andrew C. Miller, Guillermo Sapiro, Ozan Sener, Marco Cuturi Cameto, Jörn-Henrik Jacobsen
Unbalanced Low-Rank Optimal Transport Solvers
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2024
AuthorsMeyer Scetbon*, Michal Klein*, Giovanni Palla, Marco Cuturi
Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICASSPPublished year 2024
AuthorsZhihong Lei, Ernest Pusateri, Shiyi Han, Leo Liu, Mingbin Xu, Tim Ng, Ruchir Travadi, Youyuan Zhang, Mirko Hannemann, Man-Hung Siu, Zhen Huang
Deploying Attention-Based Vision Transformers to Apple Neural Engine
content type highlight research area Computer Vision, research area Speech and Natural Language ProcessingPublished year 2024
FERRET: Refer and Ground Anything Anywhere at Any Granularity
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference ICLRPublished year 2023
AuthorsHaoxuan You, Haotian (AIML) Zhang, Liangliang Cao, Zhe Gan, Bowen Zhang, Zirui Wang, Xianzhi Du, Shih-Fu Chang, Yinfei Yang
Private and Personalized Histogram Estimation in a Federated Setting
content type paper research area Methods and Algorithms, research area PrivacyWorkshop at NeurIPSPublished year 2023
AuthorsAmrith Setlur*, Vitaly Feldman*, Kunal Talwar*
ProTIP: Progressive Tool Retrieval Improves Planning
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language ProcessingPublished year 2023
AuthorsRaviteja Anantha Ramesh, Bortik Bandyopadhyay, Anirudh Kashi, Sayantan Mahinder, Andrew W Hill, Srinivas (Vasu) Chappidi
Transformers Learn Through Gradual Rank Increase
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2023
In collaboration with EPFL, Massachusetts Institute of Technology
AuthorsEnric Boix-Adsera, Etai Littwin, Emmanuel Abbe, Samy Bengio, Joshua Susskind
Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR
content type paper research area Speech and Natural Language Processingconference ASRUPublished year 2023
AuthorsSheikh Shams Azam, Tatiana Likhomanenko, Martin Pelikan, Jan "Honza" Silovsky
Advancing Speech Accessibility with Personal Voice
content type highlight research area Speech and Natural Language ProcessingPublished year 2023
Bootstrap Your Own Variance
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2023
In collaboration with University of Göttingen
AuthorsPolina Turishcheva*, Jason Ramapuram*, Sinead Williamson*, Dan Busbridge, Eeshan Dhekane, Russ Webb
Context Tuning for Retrieval Augmented Generation
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language ProcessingWorkshop at EACLPublished year 2023
AuthorsRaviteja Anantha Ramesh, Tharun Bethi, Danil Vodianik, Srinivas (Vasu) Chappidi
DataComp: In Search of the Next Generation of Multimodal Datasets
content type paper research area Computer Visionconference NeurIPSPublished year 2023
In collaboration with University of Washington
AuthorsSamir Yitzhak Gadre*, Gabriel Ilharco*, Alex Fang*, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt
Leveraging Large Language Models for Exploiting ASR Uncertainty
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsPranay Dighe, Yi (Siri) Su, Daniel Zheng, Yunshu Liu, Vineet Garg, Xiaochuan Niu, Ahmed Tewfik
Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsGautam Krishna, Sameer Dharur, Oggi Rudovic, Pranay Dighe, Saurabh Adya, Ahmed Hussen Abdelaziz, Ahmed H Tewfik
Training Large-Vocabulary Neural Language Model by Private Federated Learning for Resource-Constrained Devices
content type paper research area Privacy, research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsMingbin Xu*, Congzheng Song*, Ye Tian, Neha Agrawal, Filip Granqvist, Rogier van Dalen, Xiao Zhang, Arturo Argueta, Shiyi Han, Yaqiao Deng, Leo Liu, Anmol Walia, Alex Jin
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
content type paper research area Computer Visionconference ICLR, Workshop at NeurIPSPublished year 2023
AuthorsVimal Thilak, Omid Saremi, Preetum Nakkiran, Josh Susskind, Chen Huang, Hanlin Goh, Laurent Dinh, Etai Littwin
DeepPCR: Parallelizing Sequential Operations in Neural Networks
content type paper research area Methods and Algorithms, research area Tools, Platforms, Frameworksconference NeurIPSPublished year 2023
AuthorsFederico Danieli, Miguel Sarabia, Xavier Suau, Pau Rodríguez, Luca Zappella
HUGS: Human Gaussian Splats
content type paper research area Computer VisionPublished year 2023
In collaboration with Max Planck Institute for Intelligent Systems
AuthorsMuhammed Kocabas, Rick Chang, James Gabriel, Oncel Tuzel, Anurag Ranjan
Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models
content type paper research area Speech and Natural Language Processingconference ICASSP, Workshop at NeurIPSPublished year 2023
AuthorsDominik Wagner*, Alex Churchill*, Siddharth Sigtia, Panos Georgiou, Matt Mirsamadi, Aarshee Mishra, Erik Marchi
Controllable Music Production with Diffusion Models and Guidance Gradients
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2023
AuthorsMark Levy, Bruno Di Giorgi, Floris Weers, Angelos Katharopoulos, Tom Nickson
Fast Optimal Locally Private Mean Estimation via Random Projections
content type paper research area Methods and Algorithms, research area Privacyconference NeurIPSPublished year 2023
In collaboration with Northeastern University, University of California, Berkeley
AuthorsHilal Asi, Vitaly Feldman, Jelani Nelson, Huy L. Nguyen, Kunal Talwar
Generating Molecular Conformers with Manifold Diffusion Fields
content type paper research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2023
AuthorsYuyang Wang, Ahmed Elhag, Navdeep Jaitly, Josh Susskind, Miguel Angel Bautista Martin
How to Scale Your EMA
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2023
AuthorsDan Busbridge*, Jason Ramapuram*, Pierre Ablin*, Tatiana Likhomanenko*, Eeshan Gunesh Dhekane, Xavier Suau, Russ Webb
Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2023
AuthorsYuhui Zhang, Brandon McKinzie, Vaishaal Shankar, Zhe Gan, Alexander Toshev
4M: Massively Multimodal Masked Modeling
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2023
In collaboration with EPFL
AuthorsDavid Mizrahi*, Roman Bachmann*, Oguzhan Fatih Kar, Teresa Yeo, Mingfei Gao, Afshin Dehghan, Amir Zamir
Adaptive Weight Decay
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2023
AuthorsAmin Ghiasi, Ali Shafahi, Reza Ardekani
FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge
content type paper research area Knowledge Bases and Search, research area Tools, Platforms, Frameworksconference EMNLPPublished year 2023
AuthorsFarima Fatahi Bayat, Kun Qian, Benjamin Han, Yisi Sang, Anton Belyi, Samira Khorshidi, Fei Wu, Ihab Ilyas, Yunyao Li
One Wide Feedforward is All You Need
content type paper research area Speech and Natural Language ProcessingWorkshop at EMNLPPublished year 2023
AuthorsTelmo Pessoa Pires, António V. Lopes, Yannick Assogba, Hendra Setiawan
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
content type paper research area Speech and Natural Language Processingconference NeurIPSPublished year 2023
AuthorsIman Mirzadeh, Keivan Alizadeh, Sachin Mehta, Carlo C Del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, Mehrdad Farajtabar
Agnostically Learning Single-Index Models using Omnipredictors
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2023
AuthorsAravind Gollakota, Parikshit Gopalan, Adam R. Klivans, Konstantinos Stavropoulos
Characterizing Omniprediction via Multicalibration
content type paper research area Fairness, research area Methods and Algorithmsconference NeurIPSPublished year 2023
In collaboration with Stanford University, University of California, Berkeley
AuthorsParikshit Gopalan, Michael P. Kim, Omer Reingold
Federated Learning for Speech Recognition: Revisiting Current Trends Towards Large-Scale ASR
content type paper research area Privacy, research area Speech and Natural Language Processingconference NeurIPSPublished year 2023
AuthorsSheikh Shams Azam, Martin Pelikan, Vitaly Feldman, Kunal Talwar, Honza Silovsky, Tatiana Likhomanenko
Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs
content type paper research area Knowledge Bases and Searchconference EMNLPPublished year 2023
AuthorsSimone Conia, Min Li, Daniel Lee, Umar Farooq Minhas, Ihab IIyas, Yunyao Li
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPS, Workshop at CVPRPublished year 2023
AuthorsHaoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel, Hadi Pouransari
TiC-CLIP: Continual Training of CLIP Models
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2023
AuthorsSaurabh Garg, Hadi Pour Ansari, Mehrdad Farajtabar, Sachin Mehta, Raviteja Vemulapalli, Oncel Tuzel, Vaishaal Shankar, Fartash Faghri
What Algorithms can Transformers Learn? A Study in Length Generalization
content type paper research area Methods and Algorithmsconference ICLR, Workshop at NeurIPSPublished year 2023
AuthorsHattie Zhou, Arwen Bradley, Etai Littwin, Noam Razin, Omid Saremi, Josh Susskind, Samy Bengio, Preetum Nakkiran
Label Shift Estimators for Non-Ignorable Missing Data
content type paper research area Health, research area Methods and AlgorithmsPublished year 2023
AuthorsAndy Miller, Joe Futoma
MARRS: Multimodal Reference Resolution System
content type paper research area Speech and Natural Language Processingconference CRACPublished year 2023
Authors*Halim Cagri Ates, Shruti Bhargava, Site Li, Jiarui Lu, Siddhardha Maddula, Joel Ruben Antony Moniz, Anil Kumar Nalamalapu, Roman Hoang Nguyen, Melis Ozyildirim, Alkesh Patel, Dhivya Piraviperumal, Vincent Renkens, Ankit Samal, Thy Tran, Bo-Hsiang Tseng, Hong Yu, Yuan Zhang, Rong Zou
Automating Behavioral Testing in Machine Translation
content type paper research area Speech and Natural Language Processingconference WMTPublished year 2023
AuthorsJavier Ferrando, Matthias Sperber, Hendra Setiawan, Dominic Telaar, Saša Hasan
Diffusion Models as Masked Audio-Video Learners
content type paper research area Computer VisionWorkshop at NeurIPSPublished year 2023
AuthorsElvis Nunez, Yanzi Jin, Mohammad Rastegari, Sachin Mehta, Maxwell Horton
Improved DDIM Sampling with Moment Matching Gaussian Mixtures
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2023
AuthorsPrasad Gabbur
PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
content type paper research area Speech and Natural Language Processingconference NeurIPSPublished year 2023
AuthorsYizhe Zhang, Jiatao Gu, Zhuofeng Wu, Shuangfei Zhai, Josh Susskind, Navdeep Jaitly
EELBERT: Tiny Models through Dynamic Embeddings
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2023
AuthorsGabrielle Cohn, Rishika Agarwal, Deepanshu Gupta, Siddharth Patwardhan
SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets
content type paper research area Computer Vision, research area Methods and Algorithmsconference ACM SIGSPATIALPublished year 2023
AuthorsDaria Reshetova*, Swetava Ganguli*, C. V. Krishnakumar Iyer, Vipul Pandey
STEER: Semantic Turn Extension-Expansion Recognition for Voice Assistants
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2023
AuthorsLeon Liyang Zhang*, Jiarui Lu*, Joel Ruben Antony Moniz*, Aditya Kulkarni, Dhivya Piraviperumal, Tien Dung Tran, Nicholas Tzou, Hong Yu
Identifying Controversial Pairs in Item-to-Item Recommendations
content type paper research area Methods and Algorithmsconference RecSysPublished year 2023
AuthorsJunyi Shen*, Dayvid V. R. Oliveira*, Jin Cao, Brian Knott, Goodman Gu, Sindhu Vijaya Raghavan, Yunye Jin, Nikita Sudan, Rob Monarch
DELPHI: Data for Evaluating LLMs' Performance in Handling Controversial Issues
content type paper research area Fairness, research area Speech and Natural Language Processingconference EMNLPPublished year 2023
AuthorsDavid Q. Sun*, Artem Abzaliev*, Hadas Kotek, Zidi Xiu, Christopher Klein, Jason D. Williams
Towards Real-World Streaming Speech Translation for Code-Switched Speech
content type paper research area Speech and Natural Language ProcessingWorkshop at EMNLPPublished year 2023
In collaboration with Universitat Politècnica de Catalunya
AuthorsBelen Alastruey, Matthias Sperber, Christian Gollan, Dominic Telaar, Tim Ng, Aashish Agargwal
LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses
content type paper research area Computer Visionconference ICCVPublished year 2023
AuthorsNoah Stier, Baptiste Angles, Liang Yang, Yajie Yan, Alex Colburn, Ming Chuang
Never-ending Learning of User Interfaces
content type paper research area Computer Vision, research area Human-Computer Interactionconference UISTPublished year 2023
In collaboration with Carnegie Mellon University
AuthorsJason Wu, Rebecca Krosnick, Eldon Schoop, Amanda Swearngin, Jeffrey P. Bigham, Jeffrey Nichols
Slower Respiration Rate is Associated with Higher Self-reported Well-being After Wellness Training
content type paper research area Data Science and Annotation, research area Healthconference Nature - Scientific ReportsPublished year 2023
In collaboration with Healthy Minds Innovation, Inc.
AuthorsTammi R. A. Kral, Helen Y. Weng, Vikramjit Mitra, Theodore P. Imhoff-Smith, Erdrin Azemi, Robin I. Goldman, Melissa A. Rosenkranz, Sarah Wu, Andrew Chen, and Richard J. Davidson
When Does Optimizing a Proper Loss Yield Calibration?
content type paper research area Fairness, research area Methods and Algorithmsconference NeurIPSPublished year 2023
In collaboration with Columbia University, Stanford University
AuthorsJarosław Błasiok, Parikshit Gopalan, Lunjia Hu, Preetum Nakkiran
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICCVPublished year 2023
In collaboration with ETH Zurich, Tongji University, University of California, San Diego, University of Pennsylvania
AuthorsHansheng Chen, Jiatao Gu, Anpei Chen, Wei Tian, Zhuowen Tu, Lingjie Liu, Hao Su
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICCVPublished year 2023
AuthorsPavan Kumar Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, Anurag Ranjan
HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
content type paper research area Computer Visionconference ICCVPublished year 2023
In collaboration with Technical University of Munich
AuthorsZiya Erkoç, Fangchang Ma, Qi Shan, Matthias Nießner, Angela Dai
NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation
content type paper research area Computer VisionPublished year 2023
In collaboration with Hong Kong University of Science and Technology, Nanjing University
AuthorsJingyang Zhang, Yao Yao, Shiwei Li, Jingbo Liu, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan
Gender Bias in LLMs
content type paper research area Fairness, research area Speech and Natural Language ProcessingPublished year 2023
AuthorsHadas Kotek, Rikker Dockum, David Q. Sun
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICCVPublished year 2023
AuthorsFartash Faghri, Hadi Pouransari, Sachin Mehta, Mehrdad Farajtabar, Ali Farhadi, Mohammad Rastegari, Oncel Tuzel
Self-Supervised Object Goal Navigation with In-Situ Finetuning
content type paper research area Computer VisionPublished year 2023
In collaboration with Carnegie Mellon University
AuthorsSo Yeon Min, Yao-Hung Hubert Tsai, Wei Ding, Ali Farhadi, Ruslan Salakhutdinov, Yonatan Bisk, Jian Zhang
All About Sample-Size Calculations for A/B Testing: Novel Extensions and Practical Guide
content type paper research area Data Science and Annotation, research area Methods and Algorithmsconference CIKMPublished year 2023
AuthorsJing Zhou, Jiannan Lu, Anas Shallah
Intelligent Assistant Language Understanding On-device
content type paper research area Speech and Natural Language ProcessingPublished year 2023
AuthorsCecilia Aas, Hisham Abdelsalam, Irina Belousova, Shruti Bhargava, Jianpeng Cheng, Robert Daland, Joris Driesen, Federico Flego, Tristan Guigue, Anders Johannsen, Partha Lal, Jiarui Lu, Joel Ruben Antony Moniz, Nathan Perkins, Dhivya Piraviperumal, Stephen Pulman, Diarmuid Ó Séaghdha, David Q. Sun, John Torr, Marco Del Vecchio, Jay Wacker, Jason D. Williams, Hong Yu
Rapid and Scalable Bayesian AB Testing
content type paper research area Data Science and Annotation, research area Methods and Algorithmsconference IEEE DSAAPublished year 2023
AuthorsSrivas Chennu,* Andrew Maher,* Christian Pangerl, Subash Prabanantham, Jae Hyeon Bae, Jamie Martin, Bud Goswami
Consistent Collaborative Filtering via Tensor Decomposition
content type paper research area Knowledge Bases and Search, research area Methods and AlgorithmsPublished year 2023
AuthorsShiwen Zhao, Charles Crissman, Guillermo R Sapiro
Dataset and Network Introspection ToolKit (DNIKit)
content type paper research area Fairness, research area Tools, Platforms, FrameworksPublished year 2023
AuthorsMegan Maher Welsh, David Koski, Miguel Sarabia, Niv Sivakumar, Ian Arawjo, Aparna Joshi, Moussa Doumbouya, Xavier Suau, Luca Zappella, Nicholas Apostoloff
FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction
content type paper research area Computer Visionconference ICCVPublished year 2023
AuthorsNoah Stier, Anurag Ranjan, Alex Colburn, Yajie Yan, Liang Yang, Fangchang Ma, Baptiste Angles
Improving the Quality of Neural TTS Using Long-form Content and Multi-speaker Multi-style Modeling
content type paper research area Human-Computer Interaction, research area Speech and Natural Language ProcessingWorkshop at SSWPublished year 2023
AuthorsTuomo Raitio, Javier Latorre, Andrea Davis, Tuuli Morrill, Ladan Golipour
Voice Trigger System for Siri
content type highlight research area Speech and Natural Language ProcessingPublished year 2023
R^2: Range Regularization for Model Compression and Quantization
content type paper research area Computer Vision, research area Speech and Natural Language ProcessingPublished year 2023
AuthorsArnav Kundu*, Chungkuk Yoo*, Srijan Mishra*, Minsik Cho, Saurabh Adya
Conformalization of Sparse Generalized Linear Models
content type paper research area Methods and Algorithmsconference ICMLPublished year 2023
In collaboration with Georgia Institute of Technology
AuthorsEtash Kumar Guha, Eugene Ndiaye, Xiaoming Huo
DUET: 2D Structured and Equivariant Representations
content type paper research area Methods and Algorithmsconference ICMLPublished year 2023
AuthorsXavier Suau, Federico Danieli, T. Anderson Keller, Arno Blaas, Chen Huang, Jason Ramapuram, Dan Busbridge, Luca Zappella
PDP: Parameter-free Differentiable Pruning is All You Need
content type paper research area Methods and Algorithms, research area Tools, Platforms, Frameworksconference ICML, conference NeurIPSPublished year 2023
AuthorsMinsik Cho, Saurabh Adya, Devang Naik
Population Expansion for Training Language Models with Private Federated Learning
content type paper research area Privacy, research area Speech and Natural Language Processingconference ICMLPublished year 2023
In collaboration with University of California, San Diego
AuthorsTatsuki Koga, Congzheng Song, Martin Pelikan, Mona Chitnis
Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling
content type paper research area Methods and Algorithmsconference COLTPublished year 2023
In collaboration with Massachusetts Institute of Technology
AuthorsJason M. Altschuler, Kunal Talwar
The Role of Entropy and Reconstruction for Multi-View Self-Supervised Learning
content type paper research area Methods and Algorithmsconference ICMLPublished year 2023
AuthorsBorja Rodríguez Gálvez, Arno Blaas, Pau Rodriguez, Adam Golinski, Xavier Suau, Jason Ramapuram, Dan Busbridge, Luca Zappella
UPSCALE: Unconstrained Channel Pruning
content type paper research area Computer Visionconference ICMLPublished year 2023
AuthorsAlvin Wan, Hans Hao, Kaushik Patnaik, Sam Xu, Omer Hadad, David Guera, Zhile Ren, Qi Shan
Learning Iconic Scenes with Differential Privacy
content type highlight research area Computer Vision, research area PrivacyPublished year 2023
NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICMLPublished year 2023
In collaboration with University of California, San Diego, University of Pennsylvania
AuthorsJiatao Gu, Alex Trevithick, Kai-En Lin, Josh Susskind, Christian Theobalt, Lingjie Liu, Ravi Ramamoorthi
BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICMLPublished year 2023
AuthorsJiatao Gu, Shuangfei Zhai, Yizhe Zhang, Lingjie Liu, Josh Susskind
Referring to Screen Texts with Voice Assistants
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ACLPublished year 2023
AuthorsShruti Bhargava, Anand Dhoot, Ing-Marie Jonsson, Hoang Long Nguyen, Alkesh Patel, Hong Yu, Vincent Renkens
Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents
content type paper research area Computer Visionconference ICRAEPublished year 2023
AuthorsYao-Hung Hubert Tsai, Hanlin Goh, Ali Farhadi, Jian Zhang
5IDER: Unified Query Rewriting for Steering, Intent Carryover, Disfluencies, Entity Carryover and Repair
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2023
AuthorsJiarui Lu*, Bo-Hsiang Tseng*, Joel Ruben Antony Moniz*, Site Li, Xueyun Zhu, Hong Yu, Murat Akbacak
Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps
content type paper research area Methods and Algorithmsconference ICMLPublished year 2023
AuthorsMarco Cuturi, Michal Klein, Pierre Ablin
Private Online Prediction from Experts: Separations and Faster Rates
content type paper research area Methods and Algorithms, research area Privacyconference COLTPublished year 2023
In collaboration with Tel Aviv University
AuthorsHilal Asi*, Vitaly Feldman*, Tomer Koren*, Kunal Talwar*
Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2023
AuthorsMiguel Sarabia, Elena Menyaylenko, Alessandro Toso, Zak Aldeneh, Shadi Pirhosseinloo, Luca Zappella, Barry Theobald, Nick Apostoloff, Jonathan Sheaffer
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
content type paper research area Methods and Algorithmsconference ICMLPublished year 2023
AuthorsShuangfei Zhai*, Tatiana Likhomanenko*, Etai Littwin*, Dan Busbridge*, Jason Ramapuram*, Yizhe Zhang, Jiatao Gu, Josh M. Susskind.
The Monge Gap: A Regularizer to Learn All Transport Maps
content type paper research area Methods and Algorithmsconference ICMLPublished year 2023
AuthorsThéo Uscidda, Marco Cuturi
Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers
content type paper research area Speech and Natural Language ProcessingPublished year 2023
AuthorsHonza (Jan) Silovsky, Liuhui Deng, Arturo Argueta, Tresi Arvizo, Roger Hsiao, Sasha Kuznietsov, Yiu-Chang Lin, Xiaoqiang Xiao, Yuanyuan Zhang
Symphony: Composing Interactive Interfaces for Machine Learning
content type paper research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference CHIPublished year 2023
In collaboration with Carnegie Mellon University, Ulm University
AuthorsAlex Bäuerle*, Ángel Alexander Cabrera*, Fred Hohman, Megan Maher, David Koski, Xavier Suau, Titus Barik, Dominik Moritz
A Unifying Theory of Distance from Calibration
content type paper research area Fairness, research area Methods and Algorithmsconference ACM STOCPublished year 2023
In collaboration with Columbia University, Stanford University
AuthorsJarosław Błasiok, Parikshit Gopalan, Lunjia Hu, Preetum Nakkiran
Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2023
AuthorsMaurits Bleeker, Pawel Swietojanski, Stefan Braun, Xiaodan Zhuang
Latent Phrase Matching for Dysarthric Speech
content type paper research area Accessibility, research area Speech and Natural Language Processingconference InterspeechPublished year 2023
AuthorsColin Lea*, Dianna Yee*, Jaya Narain, Zifang Huang, Lauren Tooley, Jeffrey P. Bigham, Leah Findlater
Matching Latent Encoding for Audio-Text based Keyword Spotting
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2023
AuthorsKumari Nishu, Minsik Cho, Devang Naik
Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime
content type paper research area Methods and Algorithms, research area Privacyconference ICMLPublished year 2023
In collaboration with Tel Aviv University
AuthorsHilal Asi*, Vitaly Feldman*, Tomer Koren*, Kunal Talwar*
RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2023
In collaboration with University at Buffalo
AuthorsLiangchen Song, Liangliang Cao, Hongyu Xu, Kai Kang, Feng Tang, Junsong, Yuan, Yang Zhao
Semi-Supervised and Long-Tailed Object Detection with CascadeMatch
content type paper research area Computer Vision, research area Methods and Algorithmsconference IJCVPublished year 2023
In collaboration with Nanyang Technological University, Singapore
AuthorsYuhang Zang, Kaiyang Zhou, Chen Huang, Chen Change Loy
Less Is More: A Unified Architecture for Device-Directed Speech Detection with Multiple Invocation Types
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsOggi Rudovic, Wonil Chang, Vineet Garg, Pranay Dighe, Pramod Simha, Jack Berkowitz, Ahmed H. Abdelaziz, Sachin Kajarekar, Erik Marchi, Saurabh Adya
Collaborative Machine Learning Model Building with Families Using Co-ML
content type paper research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference IDCPublished year 2023
AuthorsTiffany Tseng, Jennifer King Chen, Mona Abdelrahman, Mary Beth Kery, Fred Hohman, Adriana Hilliard, R. Benjamin Shapiro
Efficient Multimodal Neural Networks for Trigger-less Voice Assistants
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference InterspeechPublished year 2023
AuthorsSai Srujana Buddi, Utkarsh Oggy Sarawgi, Tashweena Heeramun, Karan Sawnhey, Ed Yanosik, Saravana Rathinam, Saurabh Adya
Fast Class-Agnostic Salient Object Segmentation
content type highlight research area Computer Vision, research area Data Science and AnnotationPublished year 2023
Application-Agnostic Language Modeling for On-Device ASR
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2023
AuthorsMarkus Nussbaum-Thom, Lyan Verwimp, Youssef Oualil
Actionable Data Insights for Machine Learning
content type paper research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference EuroMLSysPublished year 2023
AuthorsManuel Bähr*, Nils Braun*, Katrin Honauer*, Ming-Chuan Wu*
Growing and Serving Large Open-domain Knowledge Graphs
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference SIGMODPublished year 2023
AuthorsIhab F. Ilyas*, JP Lacerda*, Yunyao Li*, Umar Farooq Minhas*, Ali Mousavi*, Jeffrey Pound*, Theodoros Rekatsinas*, Chiraag Sumanth*
Robustness in Multimodal Learning under Train-Test Modality Mismatch
content type paper research area Methods and Algorithmsconference ICMLPublished year 2023
AuthorsBrandon McKinzie, Joseph Cheng, Vaishaal Shankar, Yinfei Yang, Jonathon Shlens, Alexander Toshev
Learning Language-Specific Layers for Multilingual Machine Translation
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2023
AuthorsTelmo Pessoa Pires, Robin M. Schmidt, Yi-Hsiu Liao, Stephan Peitz
Modeling Spoken Information Queries for Virtual Assistants: Open Problems, Challenges and Opportunities
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference SIGIRPublished year 2023
AuthorsChristophe Van Gysel
Learning to Detect Novel and Fine-Grained Acoustic Sequences Using Pretrained Audio Representations
content type paper research area Human-Computer Interaction, research area Methods and Algorithmsconference ICASSPPublished year 2023
AuthorsVasudha Kowtha, Miquel Espi Marques, Jonathan Huang, Yichi Zhang, Carlos Avendano
PointConvFormer: Revenge of the Point-based Convolution
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2023
In collaboration with Oregon State University
AuthorsWenxuan Wu, Li Fuxin, Qi Shan
State Spaces Aren’t Enough: Machine Translation Needs Attention
content type paper research area Speech and Natural Language Processingconference EAMTPublished year 2023
In collaboration with University of Amsterdam
AuthorsAli Vardasbi*, Telmo Pessoa Pires*, Robin M. Schmidt, Stephan Peitz
Improved Speech Recognition for People Who Stutter
content type highlight research area Accessibility, research area Speech and Natural Language ProcessingPublished year 2023
AutoFocusFormer: Image Segmentation off the Grid
content type paper research area Computer Visionconference CVPRPublished year 2023
AuthorsChen Ziwen, Kaushik Patnaik, Shuangfei Zhai, Alvin Wan, Zhile Ren, Alex Schwing, Alex Colburn, Li Fuxin
Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2023
In collaboration with University of Southern California
AuthorsMozhdeh Gheini, Tatiana Likhomanenko, Matthias Sperber, Hendra Setiawan
From Robustness to Privacy and Back
content type paper research area Methods and Algorithms, research area Privacyconference ICMLPublished year 2023
AuthorsHilal Asi*, Jonathan Ullman*, Lydia Zakynthinou*
Generalization on the Unseen, Logic Reasoning and Degree Curriculum
content type paper research area Methods and Algorithmsconference ICMLPublished year 2023
In collaboration with EPFL
AuthorsEmmanuel Abbe, Samy Bengio, Aryo Lotfi, Kevin Rizk
Self-Supervised Temporal Analysis of Spatiotemporal Data
content type paper research area Computer Vision, research area Methods and Algorithmsconference IGARSSPublished year 2023
AuthorsYi Cao*, Swetava Ganguli*, Vipul Pandey
Considerations for Distribution Shift Robustness in Health
content type paper research area Health, research area Methods and Algorithmsconference ICLRPublished year 2023
AuthorsArno Blaas*, Andrew C. Miller*, Luca Zappella, Jörn-Henrik Jacobsen, Christina Heinze-Deml
f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2023
AuthorsJiatao Gu, Shuangfei Zhai, Yizhe Zhang, Miguel Ángel Bautista, Joshua M. Susskind
High-Throughput Vector Similarity Search in Knowledge Graphs
content type paper research area Knowledge Bases and Search, research area Methods and Algorithmsconference SIGMODPublished year 2023
AuthorsJason Mohoney, Anil Pacaci, Shihabur Rahman Chowdhury, Ali Mousavi, Ihab F. Ilyas, Umar Farooq Minhas, Jeffrey Pound, and Theodoros Rekatsinas
Naturalistic Head Motion Generation From Speech
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICASSPPublished year 2023
In collaboration with University of Maryland
AuthorsTrisha Mittal, Zakaria Aldeneh, Masha Fedzechkina, Anurag Ranjan, Barry-John Theobald
On the Role of Lip Articulation in Visual Speech Perception
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsZakaria Aldeneh∗, Masha Fedzechkina∗, Skyler Seto, Katherine Metcalf, Miguel Sarabia, Nicholas Apostoloff, Barry-John Theobald
FaceLit: Neural 3D Relightable Faces
content type paper research area Computer Visionconference CVPRPublished year 2023
AuthorsAnurag Ranjan, Kwang Moo Yi, Jen-Hao Rick Chang, Oncel Tuzel
Angler: Helping Machine Translation Practitioners Prioritize Model Improvements
content type paper research area Data Science and Annotation, research area Human-Computer Interactionconference CHIPublished year 2023
In collaboration with Georgia Institute of Technology, University of California, Berkeley
AuthorsSamantha Robertson*, Zijie J. Wang*, Dominik Moritz, Mary Beth Kery, Fred Hohman
Feedback Effect in User Interaction with Intelligent Assistants: Delayed Engagement, Adaption and Drop-out
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference PAKDDPublished year 2023
AuthorsZidi Xiu*, Kai-Chen Cheng*, David Q. Sun*, Jiannan Lu, Hadas Kotek, Yuhan Zhang, Paul McCarthy, Christopher Klein, Stephen Pulman, Jason D. Williams
Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsKarren Yang, Ting-Yao Hu, Jen-Hao Rick Chang, Hema Swetha Koppula, Oncel Tuzel
Pointersect: Neural Rendering with Cloud-Ray Intersection
content type paper research area Computer Visionconference CVPRPublished year 2023
In collaboration with Carnegie Mellon University, The University of British Columbia
AuthorsJen-Hao Rick Chang, Wei-Yu Chen, Anurag Ranjan, Kwang Moo Yi, Oncel Tuzel
Continuous Pseudo-Labeling from the Start
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICLRPublished year 2023
In collaboration with Carnegie Mellon University
AuthorsDan Berrebbi, Ronan Collobert, Samy Bengio, Navdeep Jaitly, Tatiana Likhomanenko
MobileOne: An Improved One millisecond Mobile Backbone
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2023
AuthorsPavan Kumar Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel and Anurag Ranjan
Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsStefan Braun, Erik McDermott, Roger Hsiao
TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2023
AuthorsDavid Berthelot, Arnaud Autef, Jierui Lin, Dian Ang Yap, Shuangfei Zhai, Siyuan Hu, Daniel Zheng, Walter Talbott, Eric Gu
Variable Attention Masking for Configurable Transformer Transducer Speech Recognition
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsPawel Swietojanski, Stefan Braun, Dogan Can, Thiago Fraga da Silva, Arnab Ghoshal, Takaaki Hori, Roger Hsiao, Henry Mason, Erik McDermott, Honza Silovsky, Ruchir Travadi, Xiaodan Zhuang
From User Perceptions to Technical Improvement: Enabling People Who Stutter to Better Use Speech Recognition
content type paper research area Accessibility, research area Speech and Natural Language Processingconference CHIPublished year 2023
AuthorsColin Lea, Zifang Huang, Jaya Narain, Lauren Tooley, Dianna Yee, Tien Dung Tran, Panayiotis Georgiou, Jeffrey Bigham, Leah Findlater
I See What You Hear: A Vision-inspired Method to Localize Words
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsMohammad Samragh, Arnav Kundu, Ting-Yao Hu, Aman Chadha, Ashish Srivastava, Minsik Cho, Oncel Tuzel, Devang Naik
More Speaking or More Speakers?
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2023
In collaboration with Carnegie Mellon University
AuthorsDan Berrebbi, Ronan Collobert, Navdeep Jaitly, Tatiana Likhomanenko
Pre-trained Model Representations and their Robustness against Noise for Speech Emotion Analysis
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsVikramjit Mitra, Vasudha Kowtha, Hsiang-Yun Sherry Chien, Erdrin Azemi, Carlos Avendano
Improvements to Embedding-Matching Acoustic-to-Word ASR Using Multiple-Hypothesis Pronunciation-Based Embeddings
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsHao Yen, Woojay Jeon
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
content type paper research area Methods and Algorithmsconference ICLRPublished year 2023
AuthorsChen Huang, Hanlin Goh, Jiatao Gu, Josh Susskind
PAEDID: Patch Autoencoder-based Deep Image Decomposition for Unsupervised Anomaly Detection
content type paper research area Computer Vision, research area Methods and Algorithmsconference IISE TransactionsPublished year 2023
In collaboration with Georgia Institute of Technology
AuthorsShancong Mou, Meng Cao, Haoping Bai, Ping Huang, Jianjun Shi, Jiulong Shan
RGI: Robust GAN-inversion for Mask-free Image Inpainting and Unsupervised Pixel-wise Anomaly Detection
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2023
In collaboration with Georgia Institute of Technology
AuthorsShancong Mou, Xiaoyi Gu, Meng Cao, Haoping Bai, Ping Huang, Jiulong Shan, Jianjun Shi
Robust Hybrid Learning With Expert Augmentation
content type paper research area Methods and AlgorithmsTransactions on Machine Learning Research (TMLR)Published year 2023
In collaboration with University of Liège
AuthorsAntoine Wehenkel, Jens Behrmann, Hsiang Hsu, Guillermo Sapiro, Gilles Louppe, Joern-Henrik Jacobsen
Self Supervision Does Not Help Natural Language Supervision at Scale
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference CVPRPublished year 2023
AuthorsFloris Weers, Vaishaal Shankar, Angelos Katharopoulos, Yinfei Yang, Tom Gunter
Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR
content type paper research area Human-Computer Interaction, research area Privacyconference ICASSPPublished year 2023
AuthorsPranay Dighe, Prateeth Nayak, Oggi Rudovic, Erik Marchi, Xiaochuan Niu, Ahmed Tewfik
FastFill: Efficient Compatible Model Update
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICLRPublished year 2023
AuthorsFlorian Jaeckle*, Fartash Faghri, Ali Farhadi, Oncel Tuzel, Hadi Pouransari*
Loss Minimization through the lens of Outcome Indistinguishability
content type paper research area Fairness, research area Methods and AlgorithmsPublished year 2023
In collaboration with Stanford University, University of California, Berkeley
AuthorsParikshit Gopalan, Lunjia Hu, Michael P. Kim, Omer Reingold, Udi Wieder
MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2023
In collaboration with University of Oxford
AuthorsKejie Li, Jia-Wang Bian, Robert Castle, Philip H.S. Torr, Victor Adrian Prisacariu
Diffusion Probabilistic Fields
content type paper research area Methods and Algorithmsconference ICLRPublished year 2023
AuthorsPeiye Zhuang, Samira Abnar, Jiatao Gu, Alex Schwing, Joshua M. Susskind, Miguel Ángel Bautista
HEiMDaL: Highly Efficient Method for Detection and Localization of wake-words
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2023
AuthorsArnav Kundu, Mohammad Samragh Razlighi, Minsik Cho, Priyanka Padmanabhan, Devang Naik
Designing Data: Proactive Data Collection and Iteration for Machine Learning
content type paper research area Fairness, research area Human-Computer InteractionPublished year 2023
In collaboration with Massachusetts Institute of Technology
AuthorsAspen Hopkins, Fred Hohman, Luca Zappella, Xavier Suau, Dominik Moritz
Improving Human Annotation Effectiveness for Fact Collection by Identifying the Most Relevant Answers
content type paper research area Data Science and Annotation, research area Knowledge Bases and Searchconference EMNLPPublished year 2023
AuthorsPranav Kamath, Yiwen Sun, Thomas Semere, Adam Green, Scott Manley, Xiaoguang Qi, Kun Qian, Yunyao Li, and Mina Farid
RangeAugment: Efficient Online Augmentation with Range Learning
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2023
AuthorsSachin Mehta, Saeid Naderiparizi, Fartash Faghri, Maxwell Horton, Lailin Chen, Ali Farhadi, Oncel Tuzel, Mohammad Rastegari
Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer
content type paper research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2022
AuthorsBenjamin Muller, Deepanshu, Gupta Siddharth, Patwardhan, Jean-Philippe Fauconnier, David Vandyke, Sachin Agarwal
Active Learning with Expected Error Reduction
content type paper research area Methods and AlgorithmsPublished year 2022
In collaboration with Stanford University, University of Washington
AuthorsSteve Mussmann, Julia Reisler, Daniel Tsai, Ehsan Mousavi, Shayne O’Brien, Moises Goldszmidt
Stable Diffusion with Core ML on Apple Silicon
content type paper research area Tools, Platforms, FrameworksPublished year 2022
AuthorsAtila Orhon, Michael Siracusa, Aseem Wadhwa
Supervised Training of Conditional Monge Maps
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2022
In collaboration with ETH Zurich
AuthorsCharlotte Bunne, Andreas Krause, Marco Cuturi
Modeling Heart Rate Response to Exercise with Wearable Data
content type paper research area Health, research area Methods and Algorithmsconference NeurIPSPublished year 2022
AuthorsAchille Nazaret*, Sana Tonekaboni*, Greg Darnell, Shirley Ren, Guillermo Sapiro, Andrew C. Miller
Shift-Curvature, SGD, and Generalization
content type paper research area Methods and AlgorithmsMachine Learning: Science and TechnologyPublished year 2022
AuthorsArwen V Bradley*, Carlos A Gomez-Uribe*, and Manish Reddy Vuyyuru
DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection
content type paper research area Computer Visionconference CVPRPublished year 2022
In collaboration with Tsinghua University
AuthorsXuan Zhang, Shiyu Li, Xi Li, Ping Huang, Jiulong Shan, Ting Chen
Symbol Guided Hindsight Priors for Reward Learning from Human Preferences
content type paper research area Human-Computer Interaction, research area Methods and Algorithmsconference NeurIPSPublished year 2022
In collaboration with Arizona State University
AuthorsMudit Verma, Katherine Metcalf
Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2022
AuthorsMelody Wolk, Andy Applebaum, Camron Dennler, Patrick Dwyer, Marina Moskowitz, Harold Nguyen, Nicole Nichols, Nicole Park, Paul Rachwalski, Frank Rau, and Adrian Webster
Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning
content type paper research area Human-Computer Interaction, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2022
AuthorsKatherine Metcalf, Miguel Sarabia, Barry-John Theobald
Homomorphic Self-Supervised Learning
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2022
AuthorsThomas Anderson Keller, Xavier Suau, Luca Zappella
Continuous Soft Pseudo-Labeling in ASR
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at NeurIPSPublished year 2022
AuthorsTatiana Likhomanenko, Ronan Collobert, Navdeep Jaitly, Samy Bengio
Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer
content type paper research area Computer Vision, research area FairnessWorkshop at NeurIPSPublished year 2022
AuthorsAndrius Ovsianas, Jason Ramapuram, Dan Busbridge, Eeshan Gunesh Dhekane, Russ Webb
Mean Estimation with User-level Privacy under Data Heterogeneity
content type paper research area Methods and Algorithms, research area Privacyconference NeurIPSPublished year 2022
AuthorsRachel Cummings*, Vitaly Feldman*, Audra McMillan*, Kunal Talwar*
Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference NeurIPSPublished year 2022
AuthorsJin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai, Huayang Li, Jian Li
Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2022
In collaboration with Cornell University, EPFL, Google
AuthorsEmmanuel Abbe, Samy Bengio, Elisabetta Cornacchia, Jon Kleinberg, Aryo Lotfi, Maithra Raghu, Chiyuan Zhang
Subspace Recovery from Heterogeneous Data with Non-isotropic Noise
content type paper research area Methods and Algorithms, research area Privacyconference NeurIPSPublished year 2022
In collaboration with Stanford University
AuthorsJohn Duchi*, Vitaly Feldman*, Lunjia Hu*, Kunal Talwar*
A Large-Scale Observational Study of the Causal Effects of a Behavioral Health Nudge
content type paper research area Health, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2022
AuthorsAchille Nazaret, Guillermo Sapiro
Improving Generalization with Physical Equations
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2022
In collaboration with Harvard University, University of Liège
AuthorsAntoine Wehenkel, Jens Behrmann, Hsiang Hsu, Guillermo Sapiro, Gilles Louppe, Joern-Henrik Jacobsen
MAEEG: Masked Auto-encoder for EEG Representation Learning
content type paper research area Health, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2022
AuthorsHsiang-Yun Sherry Chien, Hanlin Goh, Christopher M. Sandino, Joseph Y. Cheng
MBW: Multi-view Bootstrapping in the Wild
content type paper research area Computer Visionconference NeurIPSPublished year 2022
In collaboration with Carnegie Mellon University, University of Adelaide
AuthorsMosam Dabhi, Chaoyang Wang, Tim Clifford, Laszlo Jeni, Ian Fasel, Simon Lucey
Statistical Deconvolution for Inference of Infection Time Series
content type paper research area Health, research area Methods and AlgorithmsPublished year 2022
In collaboration with University of California, Berkeley
AuthorsAndrew C. Miller; Lauren A. Hannah; Joseph Futoma; Nicholas J. Foti; Emily B. Fox; Alexander D’Amour; Mark Sandler; Rif A. Saurous; Joseph A. Lewnard
APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations
content type paper research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2022
In collaboration with Carnegie Mellon University
AuthorsElan Rosenfeld, Preetum Nakkiran, Hadi Pouransari, Oncel Tuzel, Fartash Faghri
Emphasis Control for Parallel Neural TTS
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2022
AuthorsShreyas Seshadri, Tuomo Raitio, Dan Castellani, Jiangchuan Li
The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2022
AuthorsVimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss and Josh Susskind
A Treatise On FST Lattice Based MMI Training
content type paper research area Methods and AlgorithmsWorkshop at SanePublished year 2022
AuthorsAdnan Haider, Tim Ng, Zhen Huang, Xingyu Na, Antti Veikko Rosti
Non-Autoregressive Neural Machine Translation: A Call for Clarity
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2022
AuthorsRobin M. Schmidt, Telmo Pires, Stephan Peitz, Jonas Lööf
Prompting for a Conversation: How to Control a Dialog Model?
content type paper research area Speech and Natural Language ProcessingWorkshop at When Creative AI Meets Conversational AIPublished year 2022
In collaboration with University of Cambridge
AuthorsJosef Valvoda, Yimai Fang, David Vandyke
Fusion-Id: A Photoplethysmography and Motion Sensor Fusion Biometric Authenticator With Few-Shot on-Boarding
content type paper research area Health, research area Human-Computer Interactionconference ICASSPPublished year 2022
AuthorsHarshat Kumar, Hojjat Seyed Mousavi, Behrooz Shahsavari
Latent Temporal Flows for Multivariate Analysis of Wearables Data
content type paper research area Health, research area Methods and Algorithmsconference ML for HealthcarePublished year 2022
AuthorsMagda Amiridi, Gregory Darnell, Sean Jewell
The Calibration Generalization Gap
content type paper research area Methods and AlgorithmsWorkshop at ICMLPublished year 2022
AuthorsA. Michael Carrell, Neil Mallinar, James Lucas, Preetum Nakkiran
SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks
content type paper research area Computer Vision, research area Methods and Algorithmsconference ECCVPublished year 2022
In collaboration with University of Washington
AuthorsChien-Yu Lin*, Anish Prabhu*, Thomas Merth, Sachin Mehta, Anurag Ranjan, Maxwell Horton, Mohammad Rastegari
Learning Bias-reduced Word Embeddings Using Dictionary Definitions
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2022
AuthorsHaozhe An, Xiaojiang Liu, Jian Zhang
Low-Rank Optimal Transport: Approximation, Statistics and Debiasing
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2022
In collaboration with ENSAE/CREST
AuthorsMeyer Scetbon, Marco Cuturi
Safe Real-World Reinforcement Learning for Mobile Agent Obstacle Avoidance
content type paper research area Methods and Algorithms, research area Tools, Platforms, Frameworksconference BayLearnPublished year 2022
AuthorsMario Srouji, Wei Ding, Yao-Hung Hubert Tsai, Ali Farhadi, and Jian Zhang
Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference InterspeechPublished year 2022
AuthorsVikramjit Mitra, Hsiang-Yun Sherry Chien, Vasudha Kowtha, Joseph Yitan Cheng, Erdrin Azemi
Texturify: Generating Textures on 3D Shape Surfaces
content type paper research area Computer Visionconference ECCVPublished year 2022
In collaboration with Max Planck Institute for Intelligent Systems, Technical University of Munich
AuthorsYawar Siddiqui, Justus Thies, Fangchang Ma, Qi Shan, Matthias Nießner, and Angela Dai
3D Parametric Room Representation with RoomPlan
content type highlight research area Computer VisionPublished year 2022
Generative Multiplane Images: Making a 2D GAN 3D-Aware
content type paper research area Computer Visionconference ECCVPublished year 2022
In collaboration with UIUC
AuthorsXiaoming Zhao, Fangchang Ma, David Güera, Zhile Ren, Alexander G. Schwing, Alex Colburn
FLAIR: Federated Learning Annotated Image Repository
content type paper research area Computer Vision, research area Privacyconference NeurIPSPublished year 2022
AuthorsCongzheng Song, Filip Granqvist, Kunal Talwar
Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss
content type paper research area Methods and Algorithms, research area Privacyconference NeurIPSPublished year 2022
In collaboration with Massachusetts Institute of Technology
AuthorsJason M. Altschuler*, Kunal Talwar*
Two-Layer Bandit Optimization for Recommendations
content type paper research area Data Science and Annotation, research area Methods and Algorithmsconference RecSysPublished year 2022
AuthorsSiyong Ma, Puja Das, Sofia Maria Nikolakaki, Qifeng Chen, Humeyra Topcu Altintas
GAUDI: A Neural Architect for Immersive 3D Scene Generation
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2022
AuthorsMiguel Angel Bautista, Pengsheng Guo, Samira Abnar, Walter Talbott, Alexander Toshev, Zhuoyuan Chen, Laurent Dinh, Shuangfei Zhai, Hanlin Goh, Daniel Ulbricht, Afshin Dehghan, Josh Susskind
PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression
content type paper research area Health, research area Methods and Algorithmsconference CHILPublished year 2022
In collaboration with Carnegie Mellon University, UIUC, University of Michigan
AuthorsJiacheng Zhu, Gregory Darnell, Agni Kumar, Ding Zhao, Bo Li, Xuanlong Nguyen, Shirley You Ren
Toward Supporting Quality Alt Text in Computing Publications
content type paper research area Accessibility, research area Human-Computer Interactionconference W4APublished year 2022
AuthorsCandace Williams, Lilian de Greef, Ed Harris, Leah Findlater, Amy Pavel, Cynthia Bennett
Providing Insights for Open-Response Surveys via End-to-End Context-Aware Clustering
content type paper research area Human-Computer Interaction, research area Speech and Natural Language ProcessingPublished year 2022
AuthorsSoheil Esmaeilzadeh, Brian Williams, Davood Shamsi, Onar Vikingstad
Layer-Wise Data-Free CNN Compression
content type paper research area Computer Visionconference ICPRPublished year 2022
AuthorsMaxwell Horton, Yanzi Jin, Ali Farhadi, Mohammad Rastegari
RGB-X Classification for Electronics Sorting
content type paper research area Computer VisionPublished year 2022
In collaboration with Carnegie Mellon University
AuthorsFNU Abhimanyu*, Tejas Zodage*, Umesh Thillaivasan, Xinyue Lai, Rahul Chakwate, Javier Santillan, Emma Oti, Ming Zhao, Ralph Boirum Howie Choset, Matthew Travers
ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
content type paper research area Computer Visionconference ECCVPublished year 2022
In collaboration with Hong Kong University of Science and Technology
AuthorsHongkai Chen, Zixin Luo, Lei Zhou, Yurun Tian, Mingmin Zhen, Tian Fang, David Mckinnon, Yanghai Tsin, Long Quan
Mel Spectrogram Inversion with Stable Pitch
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2022
AuthorsBruno Di Giorgi*, Mark Levy*, Richard Sharp
Multi-objective Hyper-parameter Optimization of Behavioral Song Embeddings
content type paper research area Human-Computer Interaction, research area Methods and Algorithmsconference ISMIRPublished year 2022
AuthorsMassimo Quadrana, Antoine Larreche-Mouly, Matthias Mauch
Improving Voice Trigger Detection with Metric Learning
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2022
AuthorsPrateeth Nayak, Takuya Higuchi, Anmol Gupta, Shivesh Ranjan, Stephen Shum, Siddharth Sigtia, Erik Marchi, Varun Lakshminarasimhan, Minsik Cho, Saurabh Adya, Chandra Dhir, Ahmed Tewfik
NeILF: Neural Incident Light Field for Material and Lighting Estimation
content type paper research area Computer Visionconference ECCVPublished year 2022
In collaboration with Hong Kong University of Science and Technology
AuthorsYao Yao, Jingyang Zhang, Jingbo Liu, Yihang Qu, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan
Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks
content type paper research area Speech and Natural Language ProcessingPublished year 2022
In collaboration with COLING, Massachusetts Institute of Technology
AuthorsRajiv Movva*, Jinhao Lei*, Shayne Longpre, Ajay Gupta, Chris DuBois
Integrating Categorical Features in End-To-End ASR
content type paper research area Speech and Natural Language ProcessingPublished year 2022
AuthorsRongqing Huang
CVNets: High Performance Library for Computer Vision
content type paper research area Computer Vision, research area Tools, Platforms, Frameworksconference ACM MultimediaPublished year 2022
AuthorsSachin Mehta, Farzad Abdolhosseini, Mohammad Rastegari
Space-Efficient Representation of Entity-centric Query Language Models
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2022
AuthorsChristophe Van Gysel, Mirko Hannemann, Ernest Pusateri, Youssef Oualil, Ilya Oparin
A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing
content type paper research area Computer Visionconference ECCVPublished year 2022
AuthorsPaul Upchurch* and Ransen Niu*
Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2022
In collaboration with University of California, Berkeley, University of California, San Diego
AuthorsNeil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit, Mikhail Belkin, Preetum Nakkiran
FORML: Learning to Reweight Data for Fairness
content type paper research area Computer Vision, research area FairnessWorkshop at ICMLPublished year 2022
AuthorsBobby Yan*, Skyler Seto*, Nicholas Apostoloff
Regularized Training of Nearest Neighbor Language Models
content type paper research area Speech and Natural Language ProcessingWorkshop at NAACLPublished year 2022
In collaboration with University of Oxford
AuthorsJean-Francois Ton, Walter Talbott, Shuangfei Zhai, Josh Susskind
Minimax Demographic Group Fairness in Federated Learning
content type paper research area Fairness, research area Privacyconference ACM FAccTPublished year 2022
In collaboration with Duke University, University College London
AuthorsAfroditi Papadaki, Natalia Martinez, Martin Bertran, Guillermo Sapiro and Miguel Rodrigues
NeuMan: Neural Human Radiance Field from a Single Video
content type paper research area Computer VisionPublished year 2022
In collaboration with The University of British Columbia
AuthorsWei Jiang, Kwang Moo Yi, Golnoosh Samei, Oncel Tuzel, Anurag Ranjan
Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference InterspeechPublished year 2022
AuthorsVineet Garg*, Ognjen (Oggi) Rudovic*, Pranay Dighe*, Ahmed H. Abdelaziz, Erik Marchi, Saurabh Adya, Chandra Dhir, Ahmed Tewfik
Vocal Effort Modeling in Neural TTS for Improving the Intelligibility of Synthetic Speech in Noise
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference InterspeechPublished year 2022
AuthorsTuomo Raitio, Petko Petkov, Jiangchuan Li, Muhammed Shifas, Andrea Davis, Yannis Stylianou
Reachability Embeddings: Self-Supervised Representation Learning from Spatiotemporal Motion Trajectories for Multimodal Geospatial Computer Vision
content type paper research area Computer Vision, research area Methods and Algorithmsconference IEEE MDMPublished year 2022
AuthorsSwetava Ganguli, C. V. Krishnakumar Iyer, Vipul Pandey
Dynamic Memory for Interpretable Sequential Optimization
content type paper research area Data Science and Annotation, research area Methods and AlgorithmsWorkshop at KDDPublished year 2022
AuthorsSrivas Chennu*, Andrew Maher*, Jamie Martin*, Subash Prabhanantham*
ARtonomous: Introducing Middle School Students to Reinforcement Learning Through Virtual Robotics
content type paper research area Human-Computer Interactionconference ACM Interaction Design and ChildrenPublished year 2022
AuthorsGriffin Dietz, Jennifer King Chen, Jazbo Beason, Matthew Tarrow, Adriana Hilliard, and R. Benjamin Shapiro
Efficient Representation Learning via Adaptive Context Pooling
content type paper research area Methods and Algorithmsconference ICMLPublished year 2022
AuthorsChen Huang, Walter Talbott, Navdeep Jaitly, Josh Susskind
Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language ProcessingWorkshop at NAACLPublished year 2022
AuthorsZhucheng Tu, Janani Padmanabhan
Optimal Algorithms for Mean Estimation under Local Differential Privacy
content type paper research area Methods and Algorithms, research area Privacyconference ICMLPublished year 2022
In collaboration with Stanford University
AuthorsHilal Asi*, Vitaly Feldman*, Kunal Talwar*
Position Prediction as an Effective Pre-training Strategy
content type paper research area Methods and Algorithmsconference ICMLPublished year 2022
AuthorsShuangfei Zhai, Navdeep Jaitly, Tatiana Likhomanenko, Jason Ramapuram, Dan Busbridge, Walter Talbott, Chen Huang, Hanlin Goh, Joseph Yitan Cheng, Josh Susskind
Private Frequency Estimation via Projective Geometry
content type paper research area Methods and Algorithms, research area Privacyconference ICMLPublished year 2022
In collaboration with University of California, Berkeley
AuthorsVitaly Feldman*, Jelani Nelson*, Huy Nguyen*, Kunal Talwar*
Self-Conditioning Pre-Trained Language Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICMLPublished year 2022
AuthorsXavier Suau, Luca Zappella, Nicholas Apostoloff
Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICMLPublished year 2022
In collaboration with University of California, San Diego
AuthorsJen-Hao Rick Chang, Ashish Shrivastava, Hema Swetha Koppula, Xiaoshuai Zhang, Oncel Tuzel
Critical Regularizations for Neural Surface Reconstruction in the Wild
content type paper research area Computer Visionconference CVPRPublished year 2022
In collaboration with Hong Kong University of Science and Technology
AuthorsJingyang Zhang, Yao Yao, Shiwei Li, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan
A Multi-Task Neural Architecture for On-Device Scene Analysis
content type highlight research area Computer Vision, research area Methods and AlgorithmsPublished year 2022
Deploying Transformers on the Apple Neural Engine
content type highlight research area Computer Vision, research area Speech and Natural Language ProcessingPublished year 2022
Neural Face Video Compression using Multiple Views
content type paper research area Computer VisionWorkshop at CVPRPublished year 2022
AuthorsAnna Volokitin, Stefan Brugger, Ali Benlalah, Sebastian Martin, Brian Amberg, Michael Tschannen
Efficient Multi-view Stereo via Attention-Driven 2D Convolutions
content type paper research area Computer Visionconference CVPRPublished year 2022
In collaboration with University of Texas, Austin
AuthorsZhenpei Yang, Zhile Ren, Qi Shan, Qixing Huang
Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction
content type paper research area Computer Visionconference CVPRPublished year 2022
In collaboration with University of Texas, Austin
AuthorsZhenpei Yang, Zhile Ren, Miguel Angel Bautista, Zaiwei Zhang, Qi Shan, Qixing Huang
Forward Compatible Training for Large-Scale Embedding Retrieval Systems
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2022
AuthorsVivek Ramanujan*, Pavan Kumar Anasosalu Vasu, Ali Farhadi, Oncel Tuzel, Hadi Pouransari*
Bilingual End-to-End ASR with Byte-Level Subwords
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2022
AuthorsLiuhui Deng, Roger Hsiao, and Arnab Ghoshal
End-to-End Speech Translation for Code Switched Speech
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2022
AuthorsOrion Weller, Matthias Sperber, Telmo Pires, Hendra Setiawan, Christian Gollan, Dominic Telaar, Matthias Paulik
Streaming On-Device Detection of Device Directed Speech from Voice and Touch-Based Invocation
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICASSPPublished year 2022
AuthorsOggi Rudovic*, Akanksha Bindal*, Vineet Garg*, Pramod Simha*, Pranay Dighe, Sachin Kajarekar
Training a Tokenizer for Free with Private Federated Learning
content type paper research area Privacy, research area Speech and Natural Language Processingconference ACLPublished year 2022
In collaboration with Cornell Tech
AuthorsEugene Bagdasaryan, Congzheng Song, Rogier van Dalen, Matt Seigel, Áine Cahill
Utilizing Imperfect Synthetic Data to Improve Speech Recognition
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2022
AuthorsTing-Yao Hu, Mohammadreza Armandpour, Ashish Shrivastava, Jen-Hao Rick Chang, Hema Koppula, Oncel Tuzel
Data Incubation - Synthesizing Missing Data for Handwriting Recognition
content type paper research area Methods and Algorithmsconference ICASSPPublished year 2022
AuthorsJen-Hao Rick Chang, Martin Bresler, Youssouf Chherawala, Adrien Delaye, Thomas Deselaers, Ryan Dixon, Oncel Tuzel
A Platform for Continuous Construction and Serving of Knowledge At Scale
content type paper research area Knowledge Bases and Search, research area Tools, Platforms, Frameworksconference SIGMODPublished year 2022
AuthorsIhab F. Ilyas, Theodoros Rekatsinas, Vishnu Konda, Jeffrey Pound, Xiaoguang Qi, Mohamed Soliman
Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels
content type paper research area Data Science and Annotation, research area Human-Computer Interactionconference CHIPublished year 2022
In collaboration with University of Konstanz
AuthorsJochen Görtler, Fred Hohman, Dominik Moritz, Kanit Wongsuphasawat, Donghao Ren, Rahul Nair, Marc Kirchner, Kayur Patel
Low-Resource Adaptation of Open-Domain Generative Chatbots
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference ACLPublished year 2022
In collaboration with Brown University
AuthorsGreyson Gerhard-Young*, Raviteja Anantha*, Srinivas Chappidi, Björn Hoffmeister
Differentiable K-Means Clustering Layer for Neural Network Compression
content type paper research area Methods and Algorithmsconference ICLRPublished year 2022
AuthorsMinsik Cho*, Keivan A. Vahid*, Saurabh Adya, Mohammad Rastegari
Enabling Hand Gesture Customization on Wrist-Worn Devices
content type paper research area Human-Computer Interactionconference CHIPublished year 2022
In collaboration with Carnegie Mellon University, University of Washington
AuthorsXuhai Xu, Jun Gong, Carolina Brum, Lilian Liang, Bongsoo Suh, Kumar Gupta, Yash Agarwal, Laurence Lindsey, Runchang Kang, Behrooz Shahsavari, Tu Nguyen, Heriberto Nieto, Scott E. Hudson, Charlie Maalouf, Seyed Mousavi, Gierad Laput
Learning Compressed Embeddings for On-Device Inference
content type paper research area Methods and Algorithmsconference MLSysPublished year 2022
AuthorsNiketan Pansare, Jay Katukuri, Aditya Arora, Frank Cipollone, Riyaaz Shaik, Noyan Tokgozoglu and Chandru Venkataraman
Neural Fisher Kernel: Low-rank Approximation and Knowledge Distillation
content type paper research area Methods and Algorithmsconference ICLRPublished year 2022
In collaboration with Université de Montréal
AuthorsRuixiang Zhang, Shuangfei Zhai, Etai Littwin, Josh Susskind
Towards Complete Icon Labeling in Mobile Applications
content type paper research area Accessibility, research area Human-Computer Interactionconference CHIPublished year 2022
AuthorsJieshan Chen, Amanda Swearngin, Jason Wu, Titus Barik, Jeffrey Nichols and Xiaoyi Zhang
Understanding Screen Relationships from Screenshots of Smartphone Applications
content type paper research area Human-Computer Interactionconference IUIPublished year 2022
AuthorsShirin Feiz, Jason Wu, Xiaoyi Zhang, Amanda Swearngin, Titus Barik, Jeffrey Nichols
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
content type paper research area Computer Visionconference ICLRPublished year 2022
AuthorsSachin Mehta, Mohammad Rastegari
Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Survey
content type paper research area Computer Visionconference SIDPublished year 2022
AuthorsShancong Mou, Meng Cao, Zhendong Hong, Ping Huang, Jiulong Shan, Jianjun Shi
Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation
content type paper research area Methods and Algorithms, research area PrivacyPublished year 2022
AuthorsKunal Talwar
Information Gain Propagation: A New Way to Graph Active Learning with Soft Labels
content type paper research area Methods and Algorithmsconference ICLRPublished year 2022
AuthorsWentao Zhang, Yexin Wang, Zhenbang You, Meng Cao, Ping Huang, Jiulong Shan , Zhi Yang, Bin Cui
Can Open Domain Question Answering Models Answer Visual Knowledge Questions?
content type paper research area Speech and Natural Language ProcessingPublished year 2022
AuthorsJiawen Zhang, Abhijit Mishra, Avinesh P.V.S, Siddharth Patwardhan, Sachin Agarwal
Non-verbal Sound Detection for Disordered Speech
content type paper research area Accessibility, research area Speech and Natural Language Processingconference ICASSPPublished year 2022
AuthorsColin Lea, Zifang Huang, Dhruv Jain, Lauren Tooley, Zeinab Liaghat, Shrinath Thelapurath, Leah Findlater, Jeffrey P. Bigham
Hierarchical Prosody Modeling and Control in Non-Autoregressive Parallel Neural TTS
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICASSPPublished year 2022
AuthorsTuomo Raitio, Jiangchuan Li, Shreyas Seshadri
Element Level Differential Privacy: The Right Granularity of Privacy
content type paper research area PrivacyPublished year 2022
In collaboration with Stanford University
AuthorsHilal Asi, John Duchi, Omid Javidbakht
Learning Spatiotemporal Occupancy Grid Maps for Lifelong Navigation in Dynamic Scenes
content type paper research area Computer Visionconference ICRAPublished year 2022
In collaboration with University of Toronto
AuthorsHugues Thomas, Matthieu Gallet de Saint Aurin, Jian Zhang, Timothy D. Barfoot
Collaborative Filtering via Tensor Decomposition
content type paper research area Knowledge Bases and Search, research area Methods and AlgorithmsPublished year 2022
AuthorsShiwen Zhao, Charles Crissman, Guillermo R Sapiro
Modeling the Impact of User Mobility on COVID-19 Infection Rates Over Time
content type highlight research area Health, research area Methods and AlgorithmsPublished year 2022
Fast and Explicit Neural View Synthesis
content type paper research area Computer Vision, research area Methods and Algorithmsconference WACVPublished year 2022
AuthorsPengsheng Guo, Miguel Angel Bautista, Alex Colburn, Liang Yang, Daniel Ulbricht, Joshua M. Susskind, Qi Shan
Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications
content type paper research area Methods and Algorithms, research area Tools, Platforms, FrameworksPublished year 2022
AuthorsMatthias Paulik, Matt Seigel, Henry Mason, Dominic Telaar, Joris Kluivers, Rogier van Dalen, Chi Wai Lau, Luke Carlson, Filip Granqvist, Chris Vandevelde, Sudeep Agarwal, Julien Freudiger, Andrew Byde, Abhishek Bhowmick, Gaurav Kapoor, Si Beaumont, Áine Cahill, Dominic Hughes, Omid Javidbakht, Fei Dong, Rehan Rishi, Stanley Hung
Lyric Document Embeddings for Music Tagging
content type paper research area Data Science and Annotation, research area Methods and AlgorithmsPublished year 2022
AuthorsMatt McVicar, Bruno Di Giorgi, Baris Dundar, Matthias Mauch
Acoustic Neighbor Embeddings
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2022
AuthorsWoojay Jeon
Model Stability with Continuous Data Updates
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2022
AuthorsHuiting Liu, Avinesh P.V.S, Siddharth Patwardhan, Peter Grasch, Sachin Agarwal
Reconstructing Training Data from Diverse ML Models by Ensemble Inversion
content type paper research area Computer Visionconference WACVPublished year 2022
AuthorsQian Wang, Daniel Kurz
Fair SA: Sensitivity Analysis for Fairness in Face Recognition
content type paper research area Computer Vision, research area Fairnessconference NeurIPSPublished year 2021
AuthorsAparna R. Joshi, Xavier Suau, Nivedha Sivakumar, Luca Zappella, Nicholas Apostoloff
Learning Invariant Representations with Missing Data
content type paper research area Health, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2021
In collaboration with New York University
AuthorsMark Goldstein, Jörn-Henrik Jacobsen, Olina Chau, Adriel Saporta, Aahlad Puli, Rajesh Ranganath, Andrew C. Miller
Interpretable Adaptive Optimization
content type highlight research area Data Science and Annotation, research area Methods and AlgorithmsPublished year 2021
Robust Robotic Control from Pixels Using Contrastive Recurrent State-Space Models
content type paper research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2021
AuthorsNitish Srivastava, Walter Talbott, Martin Bertran Lopez, Shuangfei Zhai, Josh Susskind
Challenges of Adversarial Image Augmentations
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2021
AuthorsArno Blaas, Xavier Suau Cuadros, Jason Ramapuram, Luca Zappella, Nicholas Apostoloff
Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation
content type paper research area Data Science and Annotation, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2021
AuthorsHaoping Bai, Meng Cao, Ping Huang, Jiulong Shan
BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer
content type paper research area Computer Vision, research area Methods and Algorithmsconference NeurIPSPublished year 2021
AuthorsHaoping Bai, Meng Cao, Ping Huang, Jiulong Shan
High Fidelity 3D Reconstructions with Limited Physical Views
content type paper research area Computer Visionconference 3DVPublished year 2021
In collaboration with Carnegie Mellon University
AuthorsMosam Dabhi, Chaoyang Wang, Kunal Saluja, Laszlo A. Jeni, Ian Fasel, Simon Lucey
ARKitScenes - A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data
content type paper research area Computer Visionconference NeurIPSPublished year 2021
AuthorsGilad Baruch, Zhuoyuan Chen, Afshin Dehghan, Tal Dimry, Yuri Feigin, Peter Fu, Thomas Gebauer, Brandon Joffe, Daniel Kurz, Arik Schwartz, Elad Shulman
Do Self-Supervised and Supervised Methods Learn Similar Visual Representations?
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2021
AuthorsTom George Grigg*, Dan Busbridge*, Jason Ramapuram, Russ Webb
Enforcing Fairness in Private Federated Learning via The Modified Method of Differential Multipliers
content type paper research area Fairness, research area PrivacyWorkshop at NeurIPSPublished year 2021
AuthorsBorja Rodríguez-Gálvez, Filip Granqvist, Rogier van Dalen, Matt Seigel
Individual Privacy Accounting via a Renyi Filter
content type paper research area PrivacyWorkshop at NeurIPSPublished year 2021
AuthorsVitaly Feldman, Tijana Zrnic
Probabilistic Attention for Interactive Segmentation
content type paper research area Computer Vision, research area Data Science and Annotationconference NeurIPSPublished year 2021
AuthorsPrasad Gabbur, Manjot Bilkhu, Javier Movellan
RIM: Reliable Influence-based Active Learning on Graphs
content type paper research area Data Science and Annotation, research area Methods and Algorithmsconference NeurIPSPublished year 2021
AuthorsWentao Zhang, Yexin Wang, Zhenbang You, Meng Cao, Ping Huang, Jiulong Shan, Zhi Yang, Bin Cui
Stochastic Contrastive Learning
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at NeurIPSPublished year 2021
AuthorsJason Ramapuram*, Dan Busbridge*, Xavier Suau, Russ Webb
It’s Complicated: Characterizing The Time-varying Relationship Between Cell Phone Mobility and COVID-19 Spread in the US
content type paper research area Health, research area Methods and Algorithmsconference Nature Digital MedicinePublished year 2021
AuthorsSean Jewell, Joseph Futoma, Lauren Hannah, Andrew C. Miller, Nicholas J. Foti, Emily B. Fox
Plan-then-Generate: Controlled Data-to-Text
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2021
In collaboration with University of Cambridge
AuthorsYixuan Su, David Vandyke, Sihui Wang, Yimai Fang, Nigel Collier
Randomized Controlled Trials without Data Retention
content type paper research area Data Science and Annotation, research area Privacyconference CODEPublished year 2021
AuthorsWinston Chou
Interdependent Variables: Remotely Designing Tactile Graphics for an Accessible Workflow
content type paper research area Accessibility, research area Human-Computer Interactionconference ASSETSPublished year 2021
AuthorsLilian de Greef, Dominik Moritz, Cynthia Bennett
Breiman's Two Cultures: You Don't Have to Choose Sides
content type paper research area Health, research area Methods and Algorithmsconference Observational StudiesPublished year 2021
AuthorsAndrew C. Miller, Nicholas J. Foti, Emily B. Fox
Cross-Domain Data Integration for Entity Disambiguation in Biomedical Text
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference EMNLPPublished year 2021
In collaboration with Stanford University
AuthorsMaya Varma, Laurel Orr, Sen Wu, Megan Leszczynski, Xiao Ling and Christopher Ré
Evaluating the Fairness of Fine-Tuning Strategies in Self-Supervised Learning
content type paper research area Computer Vision, research area Fairnessconference BayLearnPublished year 2021
AuthorsJason Ramapuram*, Dan Busbridge*, Russ Webb
Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2021
AuthorsElvis Nunez*, Maxwell Horton*, Anurag Ranjan, Anish Prabhu, Ali Farhadi, Mohammad Rastegari
MMIU: Dataset for Visual Intent Understanding in Multimodal Assistants
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference WeCNLPPublished year 2021
AuthorsAlkesh Patel, Joel Ruben Antony Moniz, Roman Nguyen, Nicholas Tzou, Hadas Kotek, Vincent Renkens
On-device Neural Speech Synthesis
content type paper research area Speech and Natural Language Processingconference ASRUPublished year 2021
AuthorsSivanand Achanta, Albert Antony, Ladan Golipour, Jiangchuan Li, Tuomo Raitio, Ramya Rasipuram, Francesco Rossi, Jennifer Shi, Jaimin Upadhyay, David Winarsky, Hepeng Zhang
On-device Panoptic Segmentation for Camera Using Transformers
content type highlight research area Computer Vision, research area Methods and AlgorithmsPublished year 2021
Entity-Based Knowledge Conflicts in Question Answering
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2021
AuthorsShayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris DuBois, Sameer Singh
Finding Experts in Transformer Models
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference BayLearnPublished year 2021
AuthorsXavier Suau, Luca Zappella, Nicholas Apostoloff
DeepPRO: Deep Partial Point Cloud Registration of Objects
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICCVPublished year 2021
AuthorsDonghoon Lee, Onur C. Hamsici, Steven Feng, Prachee Sharma, Thorsten Gernoth
Using Pause Information for More Accurate Entity Recognition
content type paper research area Speech and Natural Language ProcessingWorkshop at EMNLPPublished year 2021
AuthorsSahas Dendukuri, Pooja Chitkara, Joel Ruben Antony Moniz, Xiao Yang, Manos Tsagkias, Stephen Pulman
Conditional Generation of Synthetic Geospatial Images from Pixel-Level and Feature-Level Inputs
content type paper research area Computer Visionconference BayLearnPublished year 2021
AuthorsXuerong Xiao, Swetava Ganguli, Vipul Pandey
Multi-task Learning with Cross Attention for Keyword Spotting
content type paper research area Speech and Natural Language Processingconference ASRUPublished year 2021
AuthorsTakuya Higuchi, Anmol Gupta, Chandra Dhir
Screen Parsing: Towards Reverse Engineering of UI Models from Screenshots
content type paper research area Accessibility, research area Human-Computer Interactionconference UISTPublished year 2021
AuthorsJason Wu, Xiaoyi Zhang, Jeff Nichols, Jeffrey P. Bigham
Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation
content type paper research area Computer Visionconference ICRAPublished year 2021
In collaboration with University of Toronto
AuthorsHugues Thomas, Ben Agro, Mona Gridseth, Jian Zhang, Timothy D. Barfoot
A Survey on Privacy from Statistical, Information and Estimation-Theoretic Views
content type paper research area Privacyconference IEEE BITS the Information Theory MagazinePublished year 2021
In collaboration with Duke University, Harvard University
AuthorsHsiang Hsu, Natalia Lucienne Martinezgil, Martin Bertran, Guillermo Sapiro, Flavio Calmon
Improving Neural Network Subspaces
content type highlight research area Methods and AlgorithmsPublished year 2021
Combining Speakers of Multiple Languages to Improve Quality of Neural Voices
content type paper research area Speech and Natural Language Processingconference SSWPublished year 2021
AuthorsJavier Latorre, Charlotte Bailleul, Tuuli Morrill, Alistair Conkie, Yannis Stylianou
Audiovisual Speech Synthesis using Tacotron2
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICMIPublished year 2021
AuthorsAhmed Hussen Abdelaziz*, Anushree Prasanna Kumar*, Chloe Seivwright, Gabriele Fanelli, Justin Binder, Yannis Stylianou, Sachin Kajarekar
User-Initiated Repetition-Based Recovery in Multi-Utterance Dialogue Systems
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2021
AuthorsHoang Long Nguyen, Vincent Renkens, Joris Pelemans, Srividya Pranavi Potharaju, Anil Kumar Nalamalapu, Murat Akbacak
DEXTER: Deep Encoding of External Knowledge for Named Entity Recognition in Virtual Assistants
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2021
AuthorsDeepak Muralidharan*, Joel Ruben Antony Moniz*, Weicheng Zhang, Stephen Pulman, Lin Li, Megan Barnes, Jingjing Pan, Jason Williams, Alex Acero
Managing ML Pipelines: Feature Stores and the Coming Wave of Embedding Ecosystems
content type paper research area Data Science and Annotation, research area Knowledge Bases and Searchconference VLDBPublished year 2021
AuthorsLaurel Orr, Atindriyo Sanyal, Xiao Ling, Karan Goel, Megan Leszczynski
Smooth Sequential Optimization with Delayed Feedback
content type paper research area Methods and AlgorithmsWorkshop at KDDPublished year 2021
AuthorsSrivas Chennu, Jamie Martin, Puli Liyanagama, Phil Mohr
Learning to Generate Radiance Fields of Indoor Scenes
content type highlight research area Computer Vision, research area Methods and AlgorithmsPublished year 2021
Estimating Respiratory Rate From Breath Audio Obtained Through Wearable Microphones
content type paper research area Health, research area Methods and Algorithmsconference EMBCPublished year 2021
AuthorsAgni Kumar, Vikramjit Mitra, Carolyn Oliver, Adeeti Ullal, Matt Biddulph, Irida Mance
Online Automatic Speech Recognition With Listen, Attend and Spell Model
content type paper research area Speech and Natural Language Processingconference IEEE Signal Processing LettersPublished year 2021
AuthorsRoger Hsiao, Dogan Can, Tim Ng, Ruchir Travadi, Arnab Ghoshal
Subject-Aware Contrastive Learning for Biosignals
content type paper research area Health, research area Methods and AlgorithmsPublished year 2021
AuthorsJoseph Y. Cheng, Hanlin Goh, Kaan Dogrusoz, Oncel Tuzel, Erdrin Azemi
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
content type paper research area Computer Visionconference ICCVPublished year 2021
AuthorsMike Roberts, Jason Ramapuram, Anurag Ranjan, Atulit Kumar, Miguel Angel Bautista, Nathan Paczan, Russ Webb, Joshua M. Susskind
Model-based Metrics: Sample-efficient Estimates of Predictive Model Subpopulation Performance
content type paper research area Health, research area Methods and Algorithmsconference ML for HealthcarePublished year 2021
AuthorsAndrew C. Miller, Leon A. Gatys, Joseph Futoma, Emily B. Fox
RetrievalFuse: Neural 3D Scene Reconstruction with a Database
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICCVPublished year 2021
In collaboration with Technical University of Munich
AuthorsYawar Siddiqui, Justus Thies, Fangchang Ma, Qi Shan, Matthias Nießner, Angela Dai
Joint Learning of Portrait Intrinsic Decomposition and Relighting
content type paper research area Computer VisionPublished year 2021
AuthorsMona Zehni, Shaona Ghosh, Krishna Sridhar, Sethu Raman
Non-parametric Differentially Private Confidence Intervals for the Median
content type paper research area Methods and Algorithms, research area PrivacyWorkshop at ICMLPublished year 2021
In collaboration with Boston University, Harvard University, Institute for Employment Research, University of Maryland, University of Pennsylvania
AuthorsJoerg Drechsler, Ira Globus-Harris, Audra McMillan, Jayshree Sarathy, Adam Smith
Recognizing People in Photos Through Private On-Device Machine Learning
content type highlight research area Computer Vision, research area PrivacyPublished year 2021
Unconstrained Scene Generation with Locally Conditioned Radiance Fields
content type paper research area Computer VisionWorkshop at CVPRPublished year 2021
AuthorsTerrance DeVries, Miguel Angel Bautista, Nitish Srivastava, Graham W. Taylor, Joshua M. Susskind
Trinity: A No-Code AI platform for complex spatial datasets
content type paper research area Computer VisionPublished year 2021
AuthorsC. V. Krishnakumar Iyer, Feili Hou, Henry Wang, Yonghong Wang, Kay Oh, Swetava Ganguli, Vipul Pandey
A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling
content type paper research area Methods and Algorithms, research area Privacyconference FOCSPublished year 2021
AuthorsVitaly Feldman, Audra McMillan, Kunal Talwar
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?
content type paper research area Methods and Algorithms, research area PrivacyWorkshop at ICMLPublished year 2021
In collaboration with Boston University
AuthorsGavin R Brown, Mark Bun, Vitaly Feldman, Adam Smith, Kunal Talwar
Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at ICMLPublished year 2021
AuthorsEtai Littwin, Omid Saremi, Shuangfei Zhai, Vimal Thilak, Hanlin Goh, Joshua M. Susskind, Greg Yang
A Discriminative Entity Aware Language Model for Virtual Assistants
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2021
AuthorsMandana Saebi, Ernie Pusateri, Aaksha Meghawat, Christophe Van Gysel
Analysis and Tuning of a Voice Assistant System for Dysfluent Speech
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2021
AuthorsVikramjit Mitra, Zifang Huang, Colin Lea, Lauren Tooley, Panayiotis Georgiou, Sachin Kajarekar, Jefferey Bigham
Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
content type paper research area Computer Vision, research area Methods and AlgorithmsWorkshop at ICMLPublished year 2021
AuthorsShih-Yu Sun, Vimal Thilak, Etai Littwin, Omid Saremi, Joshua M. Susskind
Learning Neural Network Subspaces
content type paper research area Computer Vision, research area Data Science and Annotationconference ICMLPublished year 2021
AuthorsMitchell Wortsman, Maxwell Horton, Carlos Guestrin, Ali Farhadi, Mohammad Rastegari
Lossless Compression of Efficient Private Local Randomizers
content type paper research area Methods and Algorithms, research area Privacyconference ICMLPublished year 2021
AuthorsVitaly Feldman, Kunal Talwar
Private Adaptive Gradient Methods for Convex Optimization
content type paper research area Methods and Algorithms, research area Privacyconference ICMLPublished year 2021
AuthorsHilal Asi, John Duchi, Alireza Fallah, Omid Javidbakht, Kunal Talwar
Private Stochastic Convex Optimization: Optimal Rates in ℓ1 Geometry
content type paper research area Methods and Algorithms, research area Privacyconference ICMLPublished year 2021
AuthorsHilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar
Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation
content type paper research area Speech and Natural Language ProcessingPublished year 2021
AuthorsVineet Garg, Wonil Chang, Siddharth Sigtia, Saurabh Adya, Pramod Simha, Pranay Dighe, Chandra Dhir
Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics
content type paper research area Methods and AlgorithmsPublished year 2021
AuthorsEtai Littwin, Greg Yang
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICMLPublished year 2021
AuthorsYue Wu, Shuangfei Zhai, Nitish Srivastava, Josh Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh
Spatio-Temporal Context for Action Detection
content type paper research area Computer VisionWorkshop at CVPRPublished year 2021
AuthorsManuel Sarmiento Calderó, David Varas, Elisenda Bou-Balust
Bootleg: Self-Supervision for Named Entity Disambiguation
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference CIDRPublished year 2021
In collaboration with Stanford University
AuthorsLaurel Orr, Megan Leszczynski, Simran Arora, Sen Wu, Neel Guha, Xiao Ling, and Christopher Ré
Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
content type paper research area Computer VisionWorkshop at CVPRPublished year 2021
AuthorsPavan Kumar Anasosalu Vasu, Shreyas Saxena, Oncel Tuzel
MorphGAN: Controllable One-Shot Face Synthesis
content type paper research area Computer Vision, research area Human-Computer InteractionWorkshop at CVPRPublished year 2021
In collaboration with Boston University
AuthorsNataniel Ruiz Gutierrez, Barry Theobald, Anurag Ranjan, Ahmed Hussen Abdelaziz, Nick Apostoloff
Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference ACLPublished year 2021
In collaboration with University of California, Irvine
AuthorsAnthony Chen, Pallavi Gudipati, Shayne Longpre, Xiao Ling, Sameer Singh
HDR Environment Map Estimation for Real-Time Augmented Reality
content type paper research area Computer Visionconference CVPRPublished year 2021
AuthorsGowri Somanath, Daniel Kurz
Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution
content type paper research area Computer VisionWorkshop at CVPRPublished year 2021
AuthorsHadi Pouransari, Mojan Javaheripi, Vinay Sharma, Oncel Tuzel
Learning to Optimize Black-Box Evaluation Metrics
content type paper research area Computer Vision, research area Methods and Algorithmsconference CVPRPublished year 2021
AuthorsChen Huang, Shuangfei Zhai, Pengsheng Guo, Josh Susskind
On the Role of Visual Cues in Audiovisual Speech Enhancement
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsZakaria Aldeneh, Anushree Prasanna Kumar, Barry-John Theobald, Erik Marchi, Sachin Kajarekar, Devang Naik, Ahmed Hussen Abdelaziz
Leveraging ML Compute for Accelerated Training on Mac
content type highlight research area Tools, Platforms, FrameworksPublished year 2021
An Attention Free Transformer
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2021
AuthorsShuangfei Zhai, Walter Talbott, Nitish Srivastava, Chen Huang, Hanlin Goh, Ruixiang Zhang, Josh Susskind
CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues
content type paper research area Speech and Natural Language Processingconference NAACLPublished year 2021
AuthorsBo-Hsiang Tseng, Shruti Bhargava, Jiarui Lu, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Lin Li, Hong Yu
Dynamic Curriculum Learning Via Data Parameters for Noise Robust Keyword Spotting
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsTakuya Higuchi, Shreyas Saxena, Mehrez Souden, Tien Dung Tran, Masood Delfarah, Chandra Dhir
Error-driven Pruning of Language Models for Virtual Assistants
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsSashank Gondala, Lyan Verwimp, Ernest Pusateri, Manos Tsagkias, Christophe Van Gysel
Knowledge Transfer for Efficient On-device False Trigger Mitigation
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsPranay Dighe, Erik Marchi, Srikanth Vishnubhotla, Sachin Kajarekar, Devang Naik
Multimodal Punctuation Prediction with Contextual Dropout
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsAndrew Silva, Barry-John Theobald, Nicholas Apostoloff
Noise-robust Named Entity Understanding for Virtual Assistants
content type paper research area Speech and Natural Language Processingconference NAACLPublished year 2021
AuthorsDeepak Muralidharan*, Joel Ruben Antony Moniz*, Sida Gao*, Xiao Yang*, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D. Williams, Lin Li
On the Transferability of Minimal Prediction Preserving Inputs in Question Answering
content type paper research area Speech and Natural Language Processingconference NAACLPublished year 2021
AuthorsShayne Longpre, Yi Lu, Christopher DuBois
Open-Domain Question Answering Goes Conversational via Question Rewriting
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference NAACLPublished year 2021
AuthorsRaviteja Anantha*, Svitlana Vakulenko*, Zhucheng Tu, Shayne Longpre, Stephen Pulman, Srinivas Chappidi
Optimize What Matters: Training DNN-HMM Keyword Spotting Model Using End Metric
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsAshish Shrivastava, Arnav Kundu, Chandra Dhir, Devang Naik, Oncel Tuzel
Progressive Voice Trigger Detection: Accuracy vs Latency
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsSiddharth Sigtia, John Bridle, Hywel Richards, Pascal Clark, Erik Marchi, Vineet Garg
SapAugment: Learning A Sample Adaptive Policy for Data Augmentation
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsTing-Yao Hu, Ashish Shrivastava, Jen-Hao Rick Chang, Hema Koppula, Stefan Braun, Kyuyeon Hwang, Ozlem Kalinli, Oncel Tuzel
Making Mobile Applications Accessible with Machine Learning
content type highlight research area Accessibility, research area Human-Computer InteractionPublished year 2021
Video Frame Interpolation via Structure-Motion based Iterative Feature Fusion
content type paper research area Computer Vision, research area Methods and Algorithmsconference SIDPublished year 2021
In collaboration with Tsinghua University, University of Science and Technology Beijing
AuthorsXi Li, Meng Cao, Yingying Tang, Scott Johnston, Zhendong Hong, Huimin Ma, Jiulong Shan
When Can Accessibility Help? An Exploration of Accessibility Feature Recommendation on Mobile Devices
content type paper research area Accessibility, research area Human-Computer Interactionconference W4APublished year 2021
AuthorsJason Wu, Gabriel Reyes, Sam C. White, Xiaoyi Zhang, Jeffrey P. Bigham
Streaming Models for Joint Speech Recognition and Translation
content type paper research area Speech and Natural Language Processingconference EACLPublished year 2021
AuthorsOrion Weller, Matthias Sperber, Christian Gollan, Joris Kluivers
Neural Feature Selection for Learning to Rank
content type paper research area Knowledge Bases and Search, research area Methods and Algorithmsconference ECIRPublished year 2021
AuthorsAlberto Purpura, Karolina Buchner, Gianmaria Silvello, Gian Antonio Susto
Generating Natural Questions from Images for Multimodal Assistants
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsAlkesh Patel, Akanksha Bindal, Hadas Kotek, Christopher Klein, Jason Williams
A Comparison of Question Rewriting Methods for Conversational Passage Retrieval
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference ECIRPublished year 2021
In collaboration with University of Amsterdam
AuthorsSvitlana Vakulenko, Nikos Voskarides, Zhucheng Tu, Shayne Longpre
Screen Recognition: Creating Accessibility Metadata for Mobile Applications from Pixels
content type paper research area Accessibility, research area Human-Computer Interactionconference CHIPublished year 2021
AuthorsXiaoyi Zhang, Lilian de Greef, Amanda Swearngin, Samuel White, Kyle Murray, Lisa Yu, Qi Shan, Jeffrey Nichols, Jason Wu, Chris Fleizach, Aaron Everitt, Jeffrey P. Bigham
Set Distribution Networks: a Generative Model for Sets of Images
content type paper research area Computer Vision, research area Methods and AlgorithmsPublished year 2021
AuthorsShuangfei Zhai, Walter Talbott, Miguel Angel Bautista, Carlos Guestrin, Josh M. Susskind
Sep-28k: A Dataset for Stuttering Event Detection from Podcasts with People Who Stutter
content type paper research area Accessibility, research area Speech and Natural Language Processingconference ICASSPPublished year 2021
AuthorsColin Lea, Vikramjit Mitra, Aparna Joshi, Sachin Kajarekar, Jeffrey Bigham
Question Rewriting for End to End Conversational Question Answering
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference WSDMPublished year 2021
AuthorsSvitlana Vakulenko, Shayne Longpre, Zhucheng Tu, Raviteja Anantha
Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language Processingconference TRECPublished year 2021
In collaboration with University of Amsterdam
AuthorsSvitlana Vakulenko, Nikos Voskarides, Zhucheng Tu, Shayne Longpre
Learning Soft Labels via Meta Learning
content type paper research area Computer VisionPublished year 2021
AuthorsNidhi Vyas, Shreyas Saxena, Thomas Voice
Whispered and Lombard Neural Speech Synthesis
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference SLTPublished year 2021
AuthorsQiong Hu, Tobias Bleisch, Petko Petkov, Tuomo Raitio, Erik Marchi, Varun Lakshminarasimhan
Frame-level SpecAugment for Deep Convolutional Neural Networks in Hybrid ASR Systems
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference SLTPublished year 2021
AuthorsXinwei Li, Yuanyuan Zhang, Xiaodan Zhuang, Daben Liu
Cinematic L1 Video Stabilization with a Log-Homography Model
content type paper research area Computer Vision, research area Methods and Algorithmsconference WACVPublished year 2020
AuthorsArwen Bradley, Jason Klivington, Joseph Triscari, Rudolph van der Merwe
On the Generalization of Learning-based 3D Reconstruction
content type paper research area Computer Vision, research area Methods and Algorithmsconference WACVPublished year 2020
AuthorsMiguel Angel Bautista, Walter Talbott, Shuangfei Zhai, Nitish Srivastava, Joshua M. Susskind
Improving Human-Labeled Data through Dynamic Automatic Conflict Resolution
content type paper research area Data Science and Annotation, research area Speech and Natural Language Processingconference COLINGPublished year 2020
AuthorsDavid Q. Sun, Hadas Kotek, Christopher Klein, Mayank Gupta, William Li, Jason D. Williams
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2020
AuthorsVitaly Feldman, Chiyuan Zhang
Collegial Ensembles
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2020
AuthorsEtai Littwin, Ben Myara, Sima Sabah, Joshua Susskind, Shuangfei Zhai, Oren Golan
Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC
content type paper research area Privacyconference NeurIPSPublished year 2020
AuthorsArun Ganesh, Kunal Talwar
On the Error Resistance of Hinge-Loss Minimization
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2020
AuthorsKunal Talwar
Representing and Denoising Wearable ECG Recordings
content type paper research area HealthWorkshop at NeurIPSPublished year 2020
AuthorsJeffrey Chan, Andrew C. Miller, Emily B. Fox
Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2020
AuthorsRaef Bassily, Vitaly Feldman, Criztobal Guzman, Kunal Talwar
Stochastic Optimization with Laggard Data Pipelines
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2020
AuthorsNaman Agarwal, Rohan Anil, Tomer Koren, Kunal Talwar, Cyril Zhang
A Wrong Answer or a Wrong Question? An Intricate Relationship between Question Reformulation and Answer Selection in Conversational Question Answering
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language ProcessingWorkshop at EMNLPPublished year 2020
AuthorsSvitlana Vakulenko, Shayne Longpre, Zhucheng Tu, Raviteja Anantha
Conversational Semantic Parsing for Dialog State Tracking
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference EMNLPPublished year 2020
AuthorsJianpeng Cheng, Devang Agrawal, Hector Martinez Alonso, Shruti Bhargava, Joris Driesen Federico Flego, Dain Kaplan, Dimitri Kartsaklis, Lin Li, Dhivya Piraviperumal, Jason D Williams, Hong Yu, Diarmuid O Seaghdha, Anders Johannsen
Efficient Inference For Neural Machine Translation
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingWorkshop at EMNLPPublished year 2020
AuthorsYi-Te Hsu, Sarthak Garg, Yi-Hsiu Liao, Ilya Chatsviorkin
How Effective is Task-Agnostic Data Augmentation for Pre-trained Transformers?
content type paper research area Methods and Algorithms, research area Speech and Natural Language Processingconference EMNLPPublished year 2020
AuthorsShayne Longpre, Yu Wang, Christopher DuBois
Generating Synthetic Images by Combining Pixel-level and Feature-level Geospatial Conditional Inputs
content type paper research area Computer Visionconference ACM SIGSPATIALPublished year 2020
In collaboration with Stanford University
AuthorsXuerong Xiao, Swetava Ganguli, Vipul Pandey
Making Smartphone Augmented Reality Apps Accessible
content type paper research area Accessibility, research area Human-Computer Interactionconference ASSETSPublished year 2020
AuthorsJaylin Herskovitz, Jason Wu, Sam White, Amy Pavel, Anhong Guo, Gabriel Reyes, Jeffrey Bigham
mage: Fluid Moves Between Code and Graphical Work in Computational Notebooks
content type paper research area Human-Computer Interaction, research area Tools, Platforms, Frameworksconference UISTPublished year 2020
In collaboration with Carnegie Mellon University, Georgia Institute of Technology
AuthorsMary Beth Kery, Donghao Ren, Fred Hohman, Dominik Moritz, Kanit Wongsuphasawat, Kayur Patel
Rescribe: Authoring and Automatically Editing Audio Descriptions
content type paper research area Accessibility, research area Human-Computer Interactionconference UISTPublished year 2020
AuthorsAmy Pavel, Gabriel Reyes, Jeffrey Bigham
Class LM and Word Mapping for Contextual Biasing in End-to-End ASR
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2020
AuthorsRongqing Huang, Ossama Abdel-hamid, Xinwei Li, Gunnar Evermann
Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2020
AuthorsRishika Agarwal, Xiaochuan Niu, Pranay Dighe, Srikanth Vishnubhotla, Sameer Badaskar, Devang Naik
Controllable Neural Text-To-Speech Synthesis Using Intuitive Prosodic Features
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference InterspeechPublished year 2020
AuthorsTuomo Raitio, Ramya Rasipuram, Dan Castellani
Hybrid Transformer and CTC Networks for Hardware Efficient Voice Triggering
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2020
AuthorsSaurabh Adya, Vineet Garg, Siddharth Sigtia, Pramod Simha, Chandra Dhir
Improving On-Device Speaker Verification Using Federated Learning With Privacy
content type paper research area Privacy, research area Speech and Natural Language Processingconference InterspeechPublished year 2020
AuthorsFilip Granqvist, Matt Seigel, Rogier van Dalen, Áine Cahill, Stephen Shum, Matthias Paulik
Stacked 1D Convolutional Networks for End-To-End Small Footprint Voice Trigger Detection
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2020
AuthorsTakuya Higuchi, Mohammad Ghasemzadeh, Kisun You, Chandra Dhir
Downbeat Tracking with Tempo-Invariant Convolutional Neural Networks
content type paper research area Methods and Algorithmsconference ISMIRPublished year 2020
AuthorsBruno Di Giorgi, Matthias Mauch, Mark Levy
Modality Dropout for Improved Performance-Driven Talking Faces
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference ICMIPublished year 2020
AuthorsAhmed Hussen Abdelaziz, Barry-John Theobald, Paul Dixon, Reinhard Knothe, Nicholas Apostoloff, Sachin Kajareker
Enhanced Direct Delta Mush
content type paper research area Methods and Algorithmsconference SIGGRAPH AsiaPublished year 2020
AuthorsSerguei Kalentchouk, Michael Hutchinson, Deepak Tolani
Learning Insulin-Glucose Dynamics in the Wild
content type paper research area Healthconference ML for HealthcarePublished year 2020
AuthorsAndrew C. Miller, Nicholas J. Foti, Emily Fox
Double-talk Robust Multichannel Acoustic Echo Cancellation Using Least Squares MIMO Adaptive Filtering: Transversal, Array, and Lattice Forms
content type paper research area Methods and AlgorithmsPublished year 2020
AuthorsSarmad Malik, Jason Wung, Joshua Atkins, Devang Naik
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering
content type paper research area Knowledge Bases and Search, research area Speech and Natural Language ProcessingPublished year 2020
AuthorsShayne Longpre, Yi Lu, Joachim Daiber
Improving Discrete Latent Representations With Differentiable Approximation Bridges
content type paper research area Computer Vision, research area Methods and Algorithmsconference IJCNNPublished year 2020
In collaboration with University of Applied Sciences, Western Switzerland, University of Geneva
AuthorsJason Ramapuram, Russ Webb
AdaScale SGD: A User-Friendly Algorithm for Distributed Training
content type paper research area Methods and Algorithmsconference ICMLPublished year 2020
AuthorsTyler B. Johnson, Pulkit Agrawal, Haijie Gu, Carlos Guestrin
A Generative Model for Joint Natural Language Understanding and Generation
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2020
AuthorsBo-Hsiang Tseng, Jianpeng Cheng, Yimai Fang, David Vandyke
Equivariant Neural Rendering
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICMLPublished year 2020
AuthorsEmilien Dupont, Miguel Angel Bautista, Alex Colburn, Aditya Sankar, Carlos Guestrin, Josh Susskind, Qi Shan
Learning to Branch for Multi-Task Learning
content type paper research area Computer Vision, research area Methods and Algorithmsconference ICMLPublished year 2020
AuthorsPengsheng Guo, Chen-Yu Lee, Daniel Ulbricht
Variational Neural Machine Translation with Normalizing Flows
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2020
AuthorsHendra Setiawan, Matthias Sperber, Udhay Nallasamy, Matthias Paulik
Predicting Entity Popularity to Improve Spoken Entity Recognition by Virtual Assistants
content type paper research area Speech and Natural Language Processingconference SIGIRPublished year 2020
AuthorsChristophe Van Gysel, Manos Tsagkias, Ernest Pusateri, Ilya Oparin
Robust Multichannel Linear Prediction for Online Speech Dereverberation Using Weighted Householder Least Squares Lattice Adaptive Filter
content type paper research area Methods and Algorithms, research area Speech and Natural Language ProcessingPublished year 2020
AuthorsJason Wung, Ante Jukić, Sarmad Malik, Mehrez Souden, Ramin Pichevar, Joshua Atkins, Devang Naik, Alex Acero
Scalable Multilingual Frontend for TTS
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
AuthorsAlistair Conkie, Andrew Finch
Generalized Reinforcement Meta Learning for Few-Shot Optimization
content type paper research area Methods and AlgorithmsWorkshop at ICMLPublished year 2020
AuthorsRaviteja Anantha, Stephen Pulman, Srinivas Chappidi
Learning to Rank Intents in Voice Assistants
content type paper research area Human-Computer Interaction, research area Speech and Natural Language Processingconference IWSDSPublished year 2020
AuthorsRaviteja Anantha, Srinivas Chappidi, Arash William Dawoodi
Detecting Emotion Primitives From Speech And Their Use In Discerning Categorical Emotions
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
AuthorsVasudha Kowtha, Vikramjit Mitra, Chris Bartels, Erik Marchi, Sue Booker, William Caruso, Sachin Kajarekar, Devang Naik
Lattice-based Improvements for Voice Triggering Using Graph Neural Networks
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
AuthorsPranay Dighe, Saurabh Adya, Nuoyu Li, Srikanth Vishnubhotla, Devang Naik, Adithya Sagar, Ying Ma, Stephen Pulman, Jason D. Williams
Automatic Class Discovery and One-Shot Interactions for Acoustic Activity Recognition
content type paper research area Accessibility, research area Human-Computer Interactionconference CHIPublished year 2020
In collaboration with Carnegie Mellon University
AuthorsJason Wu, Chris Harrison, Jeffrey P. Bigham, Gierad Laput
Tempura: Query Analysis with Structural Templates
content type paper research area Tools, Platforms, Frameworksconference CHIPublished year 2020
In collaboration with University of Washington
AuthorsTongshuang Wu, Kanit Wongsuphasawat, Donghao Ren, Kayur Patel, Chris DuBois
Understanding and Visualizing Data Iteration in Machine Learning
content type paper research area Human-Computer Interactionconference CHIPublished year 2020
In collaboration with Carnegie Mellon University, Georgia Institute of Technology
AuthorsFred Hohman, Kanit Wongsuphasawat, Mary Beth Kery, Kayur Patel
Multi-Task Learning for Voice Trigger Detection
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
AuthorsSiddharth Sigtia, Pascal Clark, Rob Haynes, Hywel Richards, John Bridle
Speech Translation and the End-to-End Promise: Taking Stock of Where We Are
content type paper research area Speech and Natural Language Processingconference ACLPublished year 2020
AuthorsMatthias Sperber, Matthias Paulik
Embedded Large-Scale Handwritten Chinese Character Recognition
content type paper research area Computer Vision, research area Speech and Natural Language Processingconference ICASSPPublished year 2020
AuthorsYoussouf Chherawala, Hans J. G. A. Dolfing, Ryan S. Dixon, Jerome R. Bellegarda
Generating Multilingual Voices Using Speaker Space Translation Based on Bilingual Speaker Data
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
In collaboration with City University of New York
AuthorsSoumi Maiti, Erik Marchi, Alistair Conkie
Leveraging GANs to Improve Continuous Path Keyboard Input Models
content type paper research area Human-Computer Interactionconference ICASSPPublished year 2020
AuthorsAkash Mehra, Jerome R. Bellegarda, Ojas Bapat, Partha Lal, Xin Wang
Least Squares Binary Quantization of Neural Networks
content type paper research area Methods and AlgorithmsWorkshop at CVPRPublished year 2020
AuthorsHadi Pouransari, Zhucheng Tu, Oncel Tuzel
Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
In collaboration with Carnegie Mellon University
AuthorsTing-Yao Hu, Ashish Shrivastava, Oncel Tuzel, Chandra Dhir
SNDCNN: Self-Normalizing Deep CNNs With Scaled Exponential Linear Units For Speech Recognition
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
AuthorsZhen Huang, Tim Ng, Leo Liu, Henry Mason, Xiaodan Zhuang, Daben Liu
On Modeling ASR Word Confidence
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
AuthorsWoojay Jeon, Maxwell Jordan, Mahesh Krishnamoorthy
Capsules with Inverted Dot-Product Attention Routing
content type paper research area Methods and Algorithmsconference ICLRPublished year 2020
In collaboration with Carnegie Mellon University
AuthorsYao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov
Improving Language Identification for Multilingual Speakers
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
In collaboration with Johns Hopkins University
AuthorsAndrew Titus, Jan Silovsky, Nanxin Chen, Roger Hsiao, Mary Young, Arnab Ghoshal
Multi-Task Learning for Speaker Verification and Voice Trigger Detection
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2020
AuthorsSiddharth Sigtia, Erik Marchi, Sachin Kajarekar, Devang Naik, John Bridle
Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well
content type paper research area Methods and Algorithmsconference ICLRPublished year 2020
In collaboration with University of California, Berkeley
AuthorsVipul Gupta, Santiago Akle Serrano, Dennis DeCoste
Adversarial Fisher Vectors for Unsupervised Representation Learning
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2019
AuthorsShuangfei Zhai, Walter Talbott, Carlos Guestrin, Joshua M. Susskind
App Usage Predicts Cognitive Ability in Older Adults
content type paper research area Accessibility, research area Healthconference CHIPublished year 2019
In collaboration with Stanford University
AuthorsMitchell L. Gordon, Leon Gatys, Carlos Guestrin, Jeffrey P. Bigham, Andrew Trister, Kayur Patel
Filter Distillation for Network Compression
content type paper research area Methods and Algorithmsconference WACVPublished year 2019
AuthorsXavier Suau, Luca Zappella, Nicholas Apostoloff
Multiple Futures Prediction
content type paper research area Methods and Algorithmsconference NeurIPSPublished year 2019
AuthorsYichuan Charlie Tang, Ruslan Salakhutdinov
An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering
content type paper research area Speech and Natural Language ProcessingWorkshop at EMNLPPublished year 2019
AuthorsShayne Longpre, Yi Lu, Zhucheng Tu, Chris DuBois
Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum
content type paper research area Data Science and Annotation, research area Methods and Algorithmsconference NeurIPSPublished year 2019
AuthorsShreyas Saxena, Oncel Tuzel, Dennis DeCoste
Nonlinear Conjugate Gradients For Scaling Synchronous Distributed DNN Training
content type paper research area Computer Visionconference NeurIPSPublished year 2019
AuthorsSaurabh Adya, Vinay Palakkode, Oncel Tuzel
Modeling Patterns of Smartphone Usage and their Relationship to Cognitive Health
content type paper research area Health, research area Human-Computer Interactionconference NeurIPSPublished year 2019
In collaboration with University of Tubingen
AuthorsJonas Rauber, Emily B. Fox, Leon A. Gatys
Worst Cases Policy Gradients
content type paper research area Methods and Algorithmsconference CoRLPublished year 2019
AuthorsYichuan Charlie Tang, Jian Zhang, Ruslan Salakhutdinov
Empirical Evaluation of Active Learning Techniques for Neural MT
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2019
In collaboration with Carnegie Mellon University
AuthorsXiangkai Zeng, Sarthak Garg, Rajen Chatterjee, Udhyakumar Nallasamy, Matthias Paulik
Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking
content type paper research area Computer VisionWorkshop at ICCVPublished year 2019
In collaboration with Canadian Institute for Advanced Research, University of Guelph, Vector Institute for Artificial Intelligence
AuthorsAlaaeldin El-Nouby, Shuangfei Zhai, Graham W. Taylor, Joshua M. Susskind
Single Training Dimension Selection for Word Embedding with PCA
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2019
AuthorsYu Wang
Overton: A Data System for Monitoring and Improving Machine-Learned Products
content type paper research area Data Science and Annotation, research area Tools, Platforms, Frameworksconference CIDRPublished year 2019
AuthorsChristopher Ré, Feng Niu, Pallavi Gudipati, Charles Srisuwananukorn
Leveraging User Engagement Signals For Entity Labeling in a Virtual Assistant
content type paper research area Speech and Natural Language ProcessingPublished year 2019
AuthorsDeepak Muralidharan, Justine Kao, Xiao Yang, Lin Li, Lavanya Viswanathan, Mubarak Seyed Ibrahim, Kevin Luikens, Stephen Pulman, Ashish Garg, Atish Kothari, Jason Williams
Reverse Transfer Learning: Can Word Embeddings Trained for Different NLP Tasks Improve Neural Language Models?
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2019
In collaboration with KU Leuven
AuthorsLyan Verwimp, Jerome R. Bellegarda
Variational Saccading: Efficient Inference for Large Resolution Images
content type paper research area Computer Visionconference BMVCPublished year 2019
In collaboration with Geneva School of Business Administration, HES-SO, University of Geneva
AuthorsJason Ramapuram, Maurits Diephuis, Frantzeska Lavda, Russ Webb, Alexandros Kalousis
Jointly Learning to Align and Translate with Transformer Models
content type paper research area Speech and Natural Language Processingconference EMNLPPublished year 2019
AuthorsSarthak Garg, Stephan Peitz, Udhyakumar Nallasamy, Matthias Paulik
Connecting and Comparing Language Model Interpolation Techniques
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2019
AuthorsErnest Pusateri, Christophe Van Gysel, Rami Botros, Sameer Badaskar, Mirko Hannemann, Youssef Oualil, Ilya Oparin
Active Learning for Domain Classification in a Commercial Spoken Personal Assistant
content type paper research area Data Science and Annotation, research area Speech and Natural Language Processingconference InterspeechPublished year 2019
AuthorsXi C. Chen, Adithya Sagar, Justine T. Kao, Tony Y. Li, Christopher Klein, Stephen Pulman, Ashish Garg, Jason D. Williams
Coarse-to-fine Optimization for Speech Enhancement
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2019
AuthorsJian Yao, Ahmad Al-Dahle
Developing Measures of Cognitive Impairment in the Real World from Consumer-Grade Multimodal Sensor Streams
content type paper research area Healthconference KDDPublished year 2019
In collaboration with Eli Lilly and Company, Evidation Health
AuthorsRichard Chen, Filip Jankovic, Nikki Marinsek, Luca Foschini, Lampros Kourtis, Alessio Signorini, Melissa Pugh, Jie Shen, Roy Yaari, Vera Maljkovic, Marc Sunga, Han Hee Song, Hyun Joon Jung, Belle Tseng, Andrew Trister
Raise to Speak: An Accurate, Low-power Detector for Activating Voice Assistants on Smartwatches
content type paper research area Human-Computer Interactionconference KDDPublished year 2019
AuthorsShiwen Zhao, Brandt Westing, Shawn Scully, Heri Nieto, Roman Holenstein, Minwoo Jeong, Krishna Sridhar, Brandon Newendorp, Mike Bastian, Sethu Raman, Tim Paek, Kevin Lynch and Carlos Guestrin
Language Identification from Very Short Strings
content type highlight research area Speech and Natural Language ProcessingPublished year 2019
AuthorsInput & Intelligence — Natural Language Processing Team
Learning Conditional Error Model for Simulated Time-Series Data
content type paper research area Methods and Algorithmsconference CVPRPublished year 2019
AuthorsAshish Shrivastava, Oncel Tuzel
Bridging the Domain Gap for Neural Models
content type highlight research area Computer VisionPublished year 2019
Improving Knowledge Base Construction from Robust Infobox Extraction
content type paper research area Knowledge Bases and Searchconference NAACLPublished year 2019
In collaboration with Sentropy Technologies
AuthorsBoya Peng, Yejin Huh, Xiao Ling, Michele Banko
Protection Against Reconstruction and Its Applications in Private Federated Learning
content type paper research area PrivacyPublished year 2019
In collaboration with Stanford University
AuthorsAbhishek Bhowmick, John Duchi, Julien Freudiger, Gaurav Kapoor, Ryan Rogers
Data Platform for Machine Learning
content type paper research area Data Science and Annotationconference SIGMODPublished year 2019
AuthorsPulkit Agrawal, Rajat Arya, Aanchal Bindal, Sandeep Bhatia, Anupriya Gagneja, Joseph Godlewski, Yucheng Low, Timothy Muss, Mudit Manu Paliwal, Sethu Raman, Vishrut Shah, Bochao Shen, Laura Sugden, Kaiyu Zhao, Ming-Chuan Wu
Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models
content type paper research area Speech and Natural Language Processingconference ICMLPublished year 2019
AuthorsAhmed Hussen Abdelaziz, Barry-John Theobald, Justin Binder, Gabriele Fanelli, Paul Dixon, Nicholas Apostoloff, Thibaut Weise, Sachin Kajareker
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
content type paper research area Methods and Algorithmsconference ICMLPublished year 2019
AuthorsChen Huang, Shuangfei Zhai, Walter Talbott, Miguel Angel Bautista, Shih-Yu Sun, Carlos Guestrin, Joshua M. Susskind
Lower Bounds for Locally Private Estimation via Communication Complexity
content type paper research area Privacyconference COLTPublished year 2019
In collaboration with Stanford University
AuthorsJohn Duchi, Ryan Rogers
Exploring Retraining-free Speech Recognition for Intra-sentential Code-switching
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2019
In collaboration with Georgia Institute of Technology
AuthorsZhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi
Parametric Cepstral Mean Normalization for Robust Speech Recognition
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2019
In collaboration with McGill University, Tencent AI Lab
AuthorsOzlem Kalinli, Gautam Bhattacharya, Chao Weng
Voice Trigger Detection from LVCSR Hypothesis Lattices Using Bidirectional Lattice Recurrent Neural Networks
content type paper research area Speech and Natural Language Processingconference ICASSPPublished year 2019
AuthorsWoojay Jeon, Leo Liu, Henry Mason
Neural Network-Based Modeling of Phonetic Durations
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2019
AuthorsXizi Wei, Melvyn Hunt, Adrian Skilling
Mirroring to Build Trust in Digital Assistants
content type paper research area Human-Computer Interactionconference InterspeechPublished year 2019
AuthorsKatherine Metcalf, Barry-John Theobald, Garrett Weinberg, Robert Lee, Ing-Marie Jonsson, Russ Webb, Nicholas Apostoloff
FoundationDB Record Layer: A Multi-Tenant Structured Datastore
content type paper research area Data Science and Annotationconference SIGMODPublished year 2019
AuthorsChristos Chrysafis, Ben Collins, Scott Dugas, Jay Dunkelberger, Moussa Ehsan, Scott Gray, Alec Grieser, Ori Herrnstadt, Kfir Lev-Ari, Tao Lin, Mike McMahon, Nicholas Schiefer, Alexander Shraer
Leveraging Acoustic Cues and Paralinguistic Embeddings to Detect Expression from Voice
content type paper research area Speech and Natural Language Processingconference InterspeechPublished year 2019
AuthorsVikramjit Mitra, Sue Booker, Erik Marchi, David Scott Farrar, Ute Dorothea Peitz, Bridget Cheng, Ermine Teves, Anuj Mehta, Devang Naik
Bandwidth Embeddings for Mixed-Bandwidth Speech Recognition
content type paper research area Privacy, research area Speech and Natural Language Processingconference InterspeechPublished year 2019
AuthorsGautam Mantena, Ozlem Kalinli, Ossama Abdel-Hamid, Don McAllaster
Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
content type paper research area Methods and Algorithmsconference CVPRPublished year 2019
AuthorsChen-Yu Lee, Tanmay Batra, Mohammad Haris Baig, Daniel Ulbricht
Towards Learning Multi-Agent Negotiations via Self-Play
content type paper research area Computer VisionWorkshop at ICCVPublished year 2019
AuthorsYichuan Charlie Tang
Optimizing Siri on HomePod in Far‑Field Settings
content type highlight research area Speech and Natural Language ProcessingPublished year 2018
AuthorsAudio Software Engineering and Siri Speech Team
Can Global Semantic Context Improve Neural Language Models?
content type highlight research area Speech and Natural Language ProcessingPublished year 2018
AuthorsFrameworks Natural Language Processing Team
A New Benchmark and Progress Toward Improved Weakly Supervised Learning
content type paper research area Methods and AlgorithmsPublished year 2018
In collaboration with University of Applied Sciences, Western Switzerland, University of Geneva
AuthorsJason Ramapuram, Russ Webb
Finding Local Destinations with Siri’s Regionally Specific Language Models for Speech Recognition
content type highlight research area Speech and Natural Language ProcessingPublished year 2018
AuthorsSiri Speech Recognition Team
Personalized Hey Siri
content type highlight research area Speech and Natural Language ProcessingPublished year 2018
AuthorsSiri Team
Structured Control Nets for Deep Reinforcement Learning
content type paper research area Computer Visionconference ICMLPublished year 2018
In collaboration with Carnegie Mellon University
AuthorsMario Srouji, Jian Zhang, Ruslan Salakhutdinov
Learning with Privacy at Scale
content type highlight research area PrivacyPublished year 2017
AuthorsDifferential Privacy Team
An On-device Deep Neural Network for Face Detection
content type highlight research area Computer Vision, research area Methods and AlgorithmsPublished year 2017
AuthorsComputer Vision Machine Learning Team
Hey Siri: An On-device DNN-powered Voice Trigger for Apple’s Personal Assistant
content type highlight research area Speech and Natural Language ProcessingPublished year 2017
AuthorsSiri Team
Real-Time Recognition of Handwritten Chinese Characters Spanning a Large Inventory of 30,000 Characters
content type highlight research area Computer VisionPublished year 2017
AuthorsHandwriting Recognition Team
Deep Learning for Siri’s Voice: On-device Deep Mixture Density Networks for Hybrid Unit Selection Synthesis
content type highlight research area Speech and Natural Language ProcessingPublished year 2017
AuthorsSiri Team
Inverse Text Normalization as a Labeling Problem
content type highlight research area Speech and Natural Language ProcessingPublished year 2017
AuthorsSiri Team
Improving Neural Network Acoustic Models by Cross-bandwidth and Cross-lingual Initialization
content type highlight research area Speech and Natural Language ProcessingPublished year 2017
AuthorsSiri Team
Learning from Simulated and Unsupervised Images through Adversarial Training
content type paper research area Computer Visionconference CVPRPublished year 2017
AuthorsAshish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda Wang, Russ Webb
Improving the Realism of Synthetic Images
content type highlight research area Computer VisionPublished year 2017

Explore advancements inMachine Learning

All research

Explore advancements in
Machine Learning