International Conference on Machine Learning (ICML) 2026
Seoul, South Korea
Apple is presenting new research at the International Conference on Machine Learning (ICML 2026), which takes place in person in Seoul, South Korea, from July 6 – 11. We are proud to again sponsor the conference, which focuses on presenting and publishing cutting-edge research in machine learning, artificial intelligence, statistics, data science, and related application areas like machine vision, computational biology, and robotics. Below is an overview of Apple’s participation at ICML 2026.
Stop by the Apple booth #B305 in Hall B1 during exhibition hours (all times referenced are in KST):
- Tuesday, July 7: 11:00 – 19:00
- Wednesday, July 8: 09:00 – 18:00
- Thursday, July 9: 09:00 – 18:00
Featured sessions
Schedule
Monday, July 6
08:00 – 09:00
Expo Talk
Apple Expo Talk at ICML 2026
Auditorium
Tuesday, July 7
08:00 – 17:00
Affinity Workshop
LatinX in AI (LXAI)
Room 300
Ana Chavarria and Luca Zappella will represent Apple during the Mentor Hour.
Mentor Hour: 16:00 — 17:00
10:15 – 10:30
Oral
Oral 1A: LLM Adaptation and Dataset Selection
Hall C
Learning Unmasking Policies for Diffusion Language Models
Metod Jazbec (University of Amsterdam), Theo X. Olausson (Massachusetts Institute of Technology), Louis Béthune, Pierre Ablin, Michael Kirchhof, Joao Monteiro, Victor Guilherme Turrisi da Costa, Jason Ramapuram, Marco Cuturi
10:30 – 12:15
Poster
Poster Session 1
Hall A
Normalized Rewards for Preference Optimization
Shawn Im (University of Wisconsin Madison), Katherine Metcalf, Barry Theobald, Skyler Seto, Federico Danieli
#1907
Multi-Agent Teams Hold Experts Back
Aneesh Pappu (Stanford University), Batu El (Stanford University), Hancheng Cao (Stanford University), Carmelo di Nolfo, Yanchao Sun, Meng Cao, James Zou (Stanford University)
#1909
Fast and Optimal Algorithms for Private Hypothesis Selection
Hilal Asi, Hongjie Chen (ETH Zurich)
#3204
11:00 – 13:00
Poster
Author Presentation at the Apple Booth
Exhibition Hall B1, #B305
14:00 – 15:45
Poster
Poster Session 2
Hall A
Residual Context Diffusion Language Models
Amir Gholami (UC Berkeley), Chenfeng Xu (UC Berkeley), Coleman Hooper (UC Berkeley), Haocheng Xi (UC Berkeley), Harman Singh (UC Berkeley), Kurt Keutzer (UC Berkeley), Michael W. Mahoney (UC Berkeley), Mehrdad Farajtabar, Monishwaran Maheswaran (UC Berkeley), Sewon Min (UC Berkeley), Yuezhou Hu (UC Berkeley)
#1915
Learning Unmasking Policies for Diffusion Language Models
Metod Jazbec (University of Amsterdam), Theo X. Olausson (Massachusetts Institute of Technology), Louis Béthune, Pierre Ablin, Michael Kirchhof, Joao Monteiro, Victor Guilherme Turrisi da Costa, Jason Ramapuram, Marco Cuturi
#2114
Cram Less to Fit More: Training Data Pruning Improves Fact Memorization
Jiayuan Ye (National University of Singapore), Vitaly Feldman, Kunal Talwar
#2310
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
Andrei Atanov (EPFL), Jesse Allardice, David Griffiths, Roman Bachmann (EPFL), Oğuzhan Fatih Kar, Devon Hjelm, Peter Fu, Amir Zamir (EPFL), Afshin Dehghan
#2506
15:00 – 17:00
Poster
Author Presentation at the Apple Booth
Exhibition Hall B1, #B305
MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers
Presenter: Han-Byul Kim
19:00 – 22:00
Affinity Workshop
Women in Machine Learning (WiML) Social
Grand Mercure Imperial Palace Seoul
Krista Shuckerow, Laura Manduchi, and Nandita Bhaskhar will represent Apple at the WiML Social.
Wednesday, July 8
09:00 – 11:30
Poster
Author Presentation at the Apple Booth
Exhibition Hall B1, #B305
09:30 – 17:00
Affinity Workshop
Women in Machine Learning (WiML) Symposium
Room E1 - E4 (3rd Floor)
Luca Zappella and Nandita Bhaskhar will represent Apple during the Mentorship Round Tables.
Mentorship Round Tables: 13:30 — 14:30
10:30 – 12:15
Poster
Poster Session 3
Hall A
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
Rosie Zhao (Harvard University), Anshul Shah, Xiaoyu Zhu, Xinke Deng, Zhongyu Jiang, Yang Yang, Joerg Liebelt, Arnab Kumar Mondal
#2016
Amortized Maximum Inner Product Search with Learned Support Functions
Theo X. Olausson (Massachusetts Institute of Technology), Joao Monteiro, Michal Klein, Marco Cuturi
#4006
13:30 – 16:00
Poster
Author Presentation at the Apple Booth
Exhibition Hall B1, #B305
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
Presenter: Arnab Kumar Mondal
14:30 – 16:15
Poster
Poster Session 4
Hall A
Learning Structured Reasoning via Tractable Trajectory Control
Po-Nien Kung (UCLA), Zhen Yang, Jeffrey Luo (UCLA), Haikang Deng (UCLA), Zi-Yi Dou (Independent Researcher), Kai-Wei Chang (UCLA), Nanyun Peng (UCLA), Yinfei Yang (Independent Researcher), Zhe Gan, Cheng-Fu Yang (UCLA)
#0316
MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers
Ajay Jaiswal, Lauren Hannah, Arnav Kundu, Duc Hoang, Han-Byul Kim, Mehrdad Farajtabar, Minsik Cho
#2003
Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
Valérie Castin (ENS & CNRS), Kimia Nadjahi (ENS & CNRS), Pierre Ablin, Gabriel Peyré (ENS & CNRS)
#2705
17:00 – 18:45
Poster
Poster Session 5
Hall A
SpecMD: A Comprehensive Study On Speculative Expert Prefetching
Duc Hoang, Mohammad Samragh Razlighi, Ajay Jaiswal, Minsik Cho
#0312
Removing Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining
Thiziri Nait Saada (University of Oxford), Louis Béthune, David Grangier, Michal Klein, Marco Cuturi, Pierre Ablin
#3801
Anti-Causal Domain Generalization: Leveraging Unlabeled Data
Sorawit Saengkyongam, Andy Miller, Jonas Peters (ETH Zürich), Juan L. Gamella (ETH Zürich), Nicolai Meinshausen (ETH Zürich), Christina Heinze-Deml
#4314
Thursday, July 9
10:30 – 12:15
Poster
Poster Session 6
Hall A
EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments
Minsoo Kim, Arnav Kundu, Han-Byul Kim, Richa Dixit, Minsik Cho
#2203
Compute When Worth It: Risk Control for Reasoning on a Compute Budget
Xi Wang (Johns Hopkins University), Anushri Suresh (Johns Hopkins University), Rishi More (Johns Hopkins University), William Jurayj (Johns Hopkins University), Benjamin Van Durme (Johns Hopkins University), Mehrdad Farajtabar, Daniel Khashabi (Johns Hopkins University), Eric Nalisnick (Johns Hopkins University)
#2301
MODUS: Decoder-only Any-to-Any Modeling of Diverse Modalities
Mingqiao Ye (EPFL), Zhaochong An (University of Copenhagen, EPFL), Zhitong Gao (EPFL), Xian Liu (The Chinese University of Hong Kong), Oğuzhan Fatih Kar, Jesse Allardice, Roman Bachmann (EPFL), David Mizrahi (Anthropic), Amir Zadeh (Lambda AI), Francois Fleuret (University of Geneva), Chuan Li (Lambda AI), Serge Belongie (University of Copenhagen), Afshin Dehghan, Amir Zamir (EPFL)
#2808
Normalizing Flows with Iterative Denoising
Tianrong Chen, Jiatao Gu, David Berthelot, Josh Susskind, Shuangfei Zhai
#4113
14:30 – 16:15
Poster
Poster Session 7
Hall A
Efficient Privacy Loss Accounting for Subsampling and Random Allocation
Vitaly Feldman, Moshe Shenfeld (Hebrew University)
#3209
Annotations Mitigate Post-Training Mode Collapse
Jacob Mitchell Springer (Carnegie Mellon University), Madhu Advani, Lukas Aichberger (Oxford), Arwen Bradley, Eran Malach, Omid Saremi, Sinead Williamson, Preetum Nakkiran, Etai Littwin, Aditi Raghunathan (Carnegie Mellon University)
#3610
17:00 – 18:45
Poster
Poster Session 8
Hall A
Optimal Splitting of Language Models from Mixtures to Specialized Domains
Skyler Seto, Pierre Ablin, Anastasiia Filippova, Jiayuan Ye (National University of Singapore), Louis Béthune, Angelos Katharopoulos, David Grangier
#1809
(1D) Ordered Tokens Enable Efficient Test-Time Search
Zhitong Gao (EPFL), Parham Rezaei (EPFL), Ali Cy (EPFL), Natasa Jovanovic (EPFL), Mingqiao Ye (EPFL), Jesse Allardice, Afshin Dehghan, Roman Bachmann EPFL), Oğuzhan Fatih Kar, Amir Zamir (EPFL)
#2504
Evaluating Sample Utility for Data Selection by Mimicking Model Weights
Brian Huang (University of Wisconsin-Madison), Manjot Bilkhu, John Cooper (University of Wisconsin-Madison), Frederic Sala (University of Wisconsin-Madison), Javier Movellan
#4404
Friday, July 10
08:00 – 17:00
Workshop
Trustworthy AI for Good Workshop 2026
Grand Ballroom 103
Poster
Distilling Self-refinement Capability for LLM faithful Summarization
Ting-Yao Hu, Hema Koppula, Hadi Pour Ansari, Cem Koc, Oncel Tuzel, Raviteja Vemulapalli
Poster
Quantifying Risk of Bias from the Use of AI Surrogates for Social Science Research
Falaah Arif Khan (New York University), Nivedha Sivakumar, Oliver Wang (Carnegie Mellon University), Katherine Metcalf, Cezanne Camacho, Barry Theobald, Luca Zappella, Nick Apostoloff
08:00 – 17:00
Workshop
Mechanistic Interpretability Workshop 2026
Hall C
Poster
Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer
Gajendra Katuwal, Advait Koparkar, Salar Abbaspourazad, Anshuman Mishra, Sarvesh Kirthivasan
Poster
Sparse Autoencoders are Capable LLM Jailbreak Mitigators
Yannick Assogba, Jacopo Cortellazzi, Javier Abad (ETH Zurich), Pau Rodriguez, Xavier Suau, Arno Blaas
08:25 – 16:30
Workshop
Learning to Listen: ICML 2026 Workshop on Machine Learning for Audio
ASEM Ballroom 202
Poster
SpeakStream: Streaming Text-to-Speech with Interleaved Data
Richard Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly
16:00 – 16:30
Workshop
Failure Modes in Agentic AI (FAGEN) Workshop 2026
Grand Ballroom 104-105
Invited Talk
Reasoning with LLMs: Challenges and Opportunities
Samy Bengio
Saturday, July 11
08:00 – 17:00
Workshop
Statistical Frameworks for Uncertainty in Agentic Systems Workshop 2026
Conf Room E1-E4
Poster
Trace Length is a Simple Uncertainty Signal in Reasoning Models
Siddartha Devic (University of Southern California ), Charlotte Peale (Stanford University), Arwen Bradley, Sinead Williamson, Preetum Nakkiran, Aravind Gollakota
Poster
Flexible Routing via Uncertainty Decomposition
Siddartha Devic (University of Southern California), Aravind Gollakota, Parikshit Gopalan, Charlotte Peale (Stanford University), Udi Wieder
08:05 – 08:50
Workshop
Planning in The Era of Language Models (LM4Plan) Workshop 2026
Grand Ballroom 101-102
Invited Talk
Reasoning with LLMs: Challenges and Opportunities
Samy Bengio
08:30 – 17:00
Workshop
Structured Data for Health Workshop 2026
Hall D2
Poster
Device Passport: Enabling Spatiotemporal Pretrained Models to Generalize Across Input Layouts
Geeling Chau (California Institute of Technology), Ran Liu, Juri Minxha, Wenhui Cui, Erdrin Azemi, Ellen Zippi, Behrooz Mahasseni, Chris Sandino
13:25 – 14:00
Workshop
Compositional Learning: Safety, Interpretability, and Agents Workshop 2026
Auditorium
Invited Talk
Reasoning with LLMs: Challenges and Opportunities
Samy Bengio
Papers
- AuthorsZhitong Gao†, Parham Rezaei†, Ali Cy†, Mingqiao Ye†, Nataša Jovanović†, Jesse Allardice, Afshin Dehghan, Amir Zamir†, Roman Bachmann†*, Oğuzhan Fatih Kar†*AuthorsTheo X. Olausson†**, João Monteiro, Michal Klein, Marco CuturiAuthorsJacob Mitchell Springer†**, Madhu Advani, Lukas Aichberger‡**, Arwen Bradley, Eran Malach, Omid Saremi, Sinead Williamson, Preetum Nakkiran, Etai Littwin, Aditi Raghunathan†AuthorsSorawit Saengkyongam†, Juan L. Gamella, Andrew C. Miller†, Jonas Peters‡, Nicolai Meinshausen‡, Christina Heinze-Deml†AuthorsValérie Castin†‡, Kimia Nadjahi†‡, Pierre Ablin, Gabriel Peyr醇AuthorsXi Wang†*, Anushri Suresh†*, Alvin Zhang†*, Rishi More†*, William Jurayj†, Benjamin Van Durme†, Mehrdad Farajtabar, Daniel Khashabi†, Eric Nalisnick†AuthorsJiayuan Ye, Vitaly Feldman, Kunal TalwarAuthorsVitaly Feldman, Moshe Shenfeld†AuthorsMinsoo Kim, Arnav Kundu, Han-Byul Kim, Richa Dixit, Minsik ChoAuthorsTzu-Heng Huang†**, Manjot Bilkhu, John Cooper†, Frederic Sala†, Javier MovellanAuthorsPo-Nien Kung†, Zhen Yang, Jeffrey Luo†, Cheng-Fu Yang†, Haikang Deng†, Zi-Yi Dou†**, Yinfei Yang**, Nanyun Peng†, Zhe Gan, Kai-Wei Chang†AuthorsLuca Moschella, Laura Manduchi, Ozan SenerAuthorsMetod Jazbec*†, Theo X. Olausson*‡, Louis Béthune, Pierre Ablin, Michael Kirchhof, João Monteiro, Victor Turrisi, Jason Ramapuram, Marco CuturiAuthorsArwen BradleyAuthorsAjay Jaiswal, Lauren Hannah, Han-Byul Kim, Duc Hoang, Arnav Kundu, Mehrdad Farajtabar, Minsik ChoAuthorsMingqiao Ye†¶, Zhaochong An†‡¶, Zhitong Gao†, Xian Liu§, Oğuzhan Fatih Kar†, Jesse Allardice, Roman Bachmann†, David Mizrahi, François Fleuret††, Chuan Li‡‡, Amir Zadeh‡‡, Serge Belongie‡, Afshin Dehghan, Amir Zamir†AuthorsAneesh Pappu†, Batu El†, Hancheng Cao‡, Carmelo di Nolfo, Yanchao Sun, Meng Cao, James Zou†AuthorsShawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine MetcalfAuthorsTianrong Chen, Jiatao Gu, David Berthelot, Joshua Susskind, Shuangfei ZhaiAuthorsRosie Zhao†**, Anshul Shah, Xiaoyu Zhu, Xinke Deng, Zhongyu Jiang, Yang Yang‡**, Joerg Liebelt, Arnab MondalAuthorsSkyler Seto, Pierre Ablin, Anastasiia Filippova, Jiayuan Ye†, Louis Béthune, Angelos Katharopoulos, David GrangierAuthorsThiziri Nait Saada‡§, Louis Bethune, Michal Klein, David Grangier, Marco Cuturi, Pierre AblinAuthorsYuezhou Hu†*, Harman Singh†*, Monishwaran Maheswaran†*, Haocheng Xi†, Coleman Hooper†, Jintao Zhang†, Aditya Tomar†, Michael W. Mahoney†, Sewon Min†, Mehrdad Farajtabar, Kurt Keutzer†, Amir Gholami†‡, Chenfeng Xu†‡AuthorsDuc Hoang, Ajay Jaiswal, Mohammad Samragh Razlighi, Minsik ChoAuthorsChen Huang, Xianhang Li, Vimal Thilak, Etai Littwin, Josh SusskindAuthorsAndrei Atanov+**, Jesse Allardice, Roman Bachmann+, Oğuzhan Fatih Kar+, Devon Hjelm, David Griffiths, Peter Fu, Afshin Dehghan, Amir Zamir+
- AuthorsGeeling Chau†**, Ran Liu, Juri Minxha, Wenhui Cui, Erdrin Azemi, Ellen L. Zippi, Behrooz Mahasseni, Christopher Michael SandinoAuthorsGajendra Katuwal, Advait Koparkar, Salar Abbaspourazad, Anshuman Mishra, Sarvesh KirthivasanAuthorsCharlotte Peale†**, Siddartha Devic‡**, Parikshit Gopalan, Udi Wieder, Aravind GollakotaAuthorsTing-Yao Hu, Hema Swetha Koppula, Hadi Pouransari, Cem Koc, Oncel Tuzel, Raviteja VemulapalliAuthorsYannick Assogba, Jacopo Cortellazzi, Javier Abad†**, Pau Rodriguez, Xavier Suau, Arno BlaasAuthorsRichard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep JaitlyAuthorsSiddhartha Devic†, Charlotte Peale‡, Arwen Bradley, Sinead Williamson, Preetum Nakkiran, Aravind Gollakota
Acknowledgements
Senior Area Chairs
Alexander Toshev, Kunal Talwar, Marco Cuturi, Pierre Ablin, Samy Bengio, Sinead Williamson, Vladlen Koltun
Area Chairs
Eran Malach, Fartash Faghri, Huangjie Zheng, Jiatao Gu, Louis Béthune, Miguel Ángel Bautista, Natalie Schluter, Ozan Sener, Peng Zhou, Tatiana Likhomanenko, Xavier Suau, Xiaoming Zhao, Vitaly Feldman
Outstanding Reviewers
Aryo Lotfi (Gold), Audra McMillan (Gold), Barry-John Theobald (Silver), Parshin Shojaee (Silver), Yannick Assogba (Silver)
Reviewers
Ariel Gao, Arnab Kumar Mondal, Duc Hoang, Ezgi Ozyilkan, Honor Chen, Luca Zappella, Minsik Cho, Minsoo Kim, Nivedha Sivakumar, Peng Zhou, Raviteja Vemulapalli, Richard Bai, Rosie Zhao, Sorawit Saengkyongam, Vimal Thilak, Xianhang Li, Xiaoming Zhao, Zakaria Aldeneh
Ethics Reviewers
Audra McMillan
Best Paper Award Committee
Marco Cuturi
Workshop Co-Organizers
Ruyuan Wan — Pluralistic Alignment Workshop 2026
Workshop Reviewers
ICML 2021
July 9, 2021research area General
Apple sponsored the thirty-eighth International Conference on Machine Learning (ICML). This conference focuses on the advancement of the branch of artificial intelligence known as machine learning and will take place virtually from July 18 to 24.
ICML 2020
July 13, 2020research area General
Apple sponsored the thirty-seventh International Conference on Machine Learning (ICML), which was held virtually from July 12 to 18. ICML is a leading global gathering dedicated to advancing the machine learning field.
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.