International Conference on Learning Representations (ICLR) 2026

Silin Gao**, Antoine Bosselut†, Samy Bengio, Emmanuel Abbe

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation

Ming Gui†‡*, Johannes Schusterbauer†‡*, Timy Phan†‡, Felix Krause†‡, Josh Susskind, Miguel Angel Bautista, Björn Ommer†‡

Adaptive Thinking: Large Language Models Know When to Think in Latent Space

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design

Deepro Choudhury†, Sinead Williamson, Adam Goliński, Ning Miao‡, Freddie Bickford Smith†, Michael Kirchhof, Yizhe Zhang, Tom Rainforth†

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity

Speech and Natural Language Processing2026

Amir Joudaki†, Giulia Lanzillotta†, Mohammad Samragh Razlighi, Iman Mirzadeh, Keivan Alizadeh, Thomas Hofmann†, Mehrdad Farajtabar, Fartash Faghri

Closing the Gap Between Text and Speech Understanding in LLMs

Santiago Cuervo†, Skyler Seto, Maureen de Seyssel, Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly, Zakaria Aldeneh

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration

Methods and Algorithms, Speech and Natural Language Processing2025

Bruno Mlodozeniec†**, Pierre Ablin, Louis Béthune, Dan Busbridge, Michal Klein, Jason Ramapuram, Marco Cuturi

Compute-Optimal Quantization-Aware Training

Aleksandr Dremov**†, David Grangier, Angelos Katharopoulos, Awni Hannun

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

Methods and Algorithms, Speech and Natural Language Processing2025

Huangjie Zheng, Shansan Gong‡**, Ruixiang Zhang, Tianrong Chen, Jiatao Gu,, Mingyuan Zhou†**, Navdeep Jaitly, Yizhe Zhang

Data-Centric Lessons To Improve Speech-Language Pretraining

Speech and Natural Language Processing2025

Vishaal Udandarao†‡, Zhiyun Lu, Xuankai Chang, Yongqiang Wang, Violet Z. Yao, Albin Madapally Jose, Fartash Faghri, Josh Gardner, Chung-Cheng Chiu

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

Speech and Natural Language Processing2026

Shansan Gong†**, Ruixiang Zhang, Huangjie Zheng, Jiatao Gu, Navdeep Jaitly, Lingpeng Kong†**, Yizhe Zhang

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

Computer Vision, Data Science and Annotation2025

Ryan Hoque*, Peide Huang*, David J. Yoon*, Mouli Sivapurapu, Jian Zhang

EMBridge: Enhancing Gesture Generalization from EMG Signals through Cross-Modal Representation Learning

Human-Computer Interaction, Methods and Algorithms2026

Wenhui Cui†**, Christopher M. Sandino, Hadi Pouransar, Ran Liu, Juri Minxha, Ellen L. Zippi, Erdrin Azemi, Behrooz Mahasseni

Entropy-Preserving Reinforcement Learning

Computer Vision, Methods and Algorithms2026

Aleksei Petrenko‡, Ben Lipkin†‡**, Kevin Chen, Erik Wijmans, Marco Cusumano-Towner, Raja Giryes, Philipp Krähenbühl

Flow Matching with Semidiscrete Couplings

Stephen Zhang**, Seyed Alireza Mousavi Hosseini**, Michal Klein, Marco Cuturi

FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models

Speech and Natural Language Processing2025

Amin Karimi Monsefi†‡, Nikhil Bhendawade, Manuel R. Ciosici, Dominic Culver, Yizhe Zhang, Irina Belousova

GenCtrl -- A Formal Controllability Toolkit for Generative Models

Methods and Algorithms, Speech and Natural Language Processing2025

Emily Cheng†, Carmen Amo Alonso‡, Federico Danieli, Arno Blaas, Luca Zappella, Pau Rodríguez, Xavier Suau

GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning

Silvia Sapora**, Devon Hjelm, Alexander Toshev, Omar Attia, Bogdan Mazoure

Hilbert: Recursively Building Formal Proofs with Informal Reasoning

Methods and Algorithms, Tools, Platforms, Frameworks2025

Sumanth Varambally**†, Thomas Voice, Yanchao Sun, Zhifeng Chen, Rose Yu†, Ke Ye

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning

Murray Kang (UCSD), Yizhe Zhang, Nikki Kuang (UCSD), Nicklas Majamaki (UCSD), Navdeep Jaitly, Yian Ma (UCSD), Lianhui Qin (UCSD)

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

Wei Liu (HKUST), Ruochen Zhou (HKUST), Yiyun Deng (HKUST), Yuzhen Huang (HKUST), Jaunting Liu (HLUST), Yuntian Deng (University of Waterloo), Yizhe Zhang, Junxian He (HKUST)

Learning to Reason as Action Abstractions with Scalable Mid-Training RL

Data Science and Annotation, Methods and Algorithms2026

Shenao Zhang†**, Donghan Yu, Yihao Feng, Bowen Jin‡**, Zhaoran Wang†, John Peebles**, Zirui Wang

Learning to Reason for Hallucination Span Detection

Methods and Algorithms, Speech and Natural Language Processing2026

Hsuan Su†, Ting-Yao Hu, Hema Swetha Koppula, Kundan Krishna, Hadi Pouransari, Cheng-Yu Hsieh, Cem Koc, Joseph Yitan Cheng, Oncel Tuzel, Raviteja Vemulapalli

Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

Computer Vision2026

Yixing Lao†**, Xuyang Bai, Xiaoyang Wu†, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao†

LiTo: Surface Light Field Tokenization

Computer Vision, Methods and Algorithms2026

Jen-Hao Rick Chang‡, Xiaoming Zhao‡, Dorian Chan, Oncel Tuzel

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Computer Vision2026

Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang†**, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter, Zirui Wang, Guoli Yin, Zhengdong Zhang, Chen Chen, Yang Zhao, Ruoming Pang†**, Zhifeng Chen

MobileCLIP2: Improving Multi-Modal Reinforced Training

Fartash Faghri*, Pavan Kumar Anasossalu Vasu*, Cem Koc, Vaishaal Shankar†, Alexander Toshev, Oncel Tuzel, Hadi Pouransari

On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment

Methods and Algorithms, Tools, Platforms, Frameworks2026

Sarah Ball†, Greg Gluch‡, Shafi Goldwasser‡, Frauke Kreuter†§, Omer Reingold¶, Guy N. Rothblum

ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models

Federico Danieli, Pau Rodriguez, Miguel Sarabia, Xavier Suau, Luca Zappella

Pretraining with Hierarchical Memories: Separating Long-Tail and Common Knowledge

Knowledge Bases and Search, Methods and Algorithms2026

Hadi Pouransari, David Grangier, C Thomas, Michael Kirchhof, Oncel Tuzel

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers

Knowledge Bases and Search, Methods and Algorithms2025

Xianhang Li†, Chen Huang, Chun-Liang Li, Eran Malach, Josh Susskind, Vimal Thilak, Etai Littwin

Reusing Pre-Training Data at Test Time is a Compute Multiplier

Alex Fang†**, Thomas Voice, Ruoming Pang**, Ludwig Schmidt†, Tom Gunter**

Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training

Methods and Algorithms, Speech and Natural Language Processing2026

Jakub Krajewski**, Amitis Shidani, Dan Busbridge, Sam Wiseman, Jason Ramapuram

RL for Reasoning by Adaptively Revealing Rationales

Data Science and Annotation, Methods and Algorithms2026

Mohammad Hossein Amani†, Aryo Lotfi†, Nicolas Mario Baldwin†, Samy Bengio, Mehrdad Farajtabar, Emmanuel Abbé*, Robert West*†

Scaling Synthetic Task Generation for Agents via Exploration

Ram Ramrakhya**, Andrew Szot, Omar Attia, Yuhao Yang, Anh Nguyen, Bogdan Mazoure, Zhe Gan, Harsh Agrawal, Alexander Toshev

SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?

Speech and Natural Language Processing2026

Michael Kirchhoff, Luca Füger†, Adam Goliński, Eeshan Gunesh Dhekane, Arno Blaas, Seong Joon Oh‡, Sinead Williamson

Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language

Human-Computer Interaction, Methods and Algorithms2025

Angie Boggust†, Donghao Ren, Yannick Assogba, Dominik Moritz, Arvind Satyanarayan†, Fred Hohman

Sharp Monocular View Synthesis in Less Than a Second

Lars Mescheder, Wei Dong, Shiwei Li, Xuyang Bai, Marcel Santos, Peiyun Hu, Bruno Lecouat, Mingmin Zhen, Amaël Delaunoy, Tian Fang, Yanghai Tsin, Stephan R. Richter, Vladlen Koltun

SimpleFold: Folding Proteins is Simpler than You Think

Speech and Natural Language Processing2025

Yuyang Wang, Jiarui Lu**, Navdeep Jaitly, Josh Susskind, Miguel Angel Bautista

Synthetic Bootstrapped Pretraining

Zitong Yang†‡, Aonan Zhang‡, Hong Liu†, Tatsunori Hashimoto†, Emmanuel Candès†, Chong Wang, Ruoming Pang

The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics

Methods and Algorithms, Speech and Natural Language Processing2026

Gregor Bachmann, Yichen Jiang, Seyed Mohsen Moosavi Dezfooli, Moin Nabi

To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models

Methods and Algorithms, Tools, Platforms, Frameworks2026

Eran Malach, Omid Saremi, Sinead Williamson, Arwen Bradley, Aryo Lotfi, Emmanuel Abbe, Josh Susskind, Etai Littwin

Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs

Computer Vision, Speech and Natural Language Processing2026

Preetum Nakkiran, Arwen Bradley, Adam Goliński, Eugene Ndiaye, Michael Kirchhof, Sinead Williamson

VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety

Shruti Palaskar, Leon Gatys, Mona Abdelrahman, Mar Jacobo, Larry Lindsey, Rutika Moharir, Gunnar Lund, Yang Xu, Navid Shiee, Jeffrey Bigham, Charles Maalouf, Joseph Yitan Cheng

Workshop Papers

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts

Methods and Algorithms, Speech and Natural Language Processing2026

Jiayuan Ye, Vitaly Feldman, Kunal Talwar

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment

Methods and Algorithms, Speech and Natural Language Processing2025

Kundan Krishna, Joseph Y Cheng, Charles Maalouf, Leon A Gatys

LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss