2026年国際学習表現会議（ICLR）におけるアップルの発表
Appleは、2026年4月23日から27日にブラジル・リオデジャネイロで開催される国際会議ICLRにスポンサーとして参加し、新たな研究を発表する予定である。
キーポイント
AppleのICLR 2026への参加
Appleは、2026年4月23日から27日にブラジル・リオデジャネイロで開催されるInternational Conference on Learning Representations (ICLR)に参加し、新たな研究を発表する。
Appleのスポンサーシップ
Appleは、ディープラーニングに焦点を当てた科学および産業研究コミュニティを結集するICLR会議を再びスポンサーしている。
会議の概要
ICLRは、ディープラーニングに焦点を当てた科学および産業研究コミュニティを結集する年次国際会議である。
影響分析・編集コメントを表示
影響分析
この記事は、Appleが主要なAI研究コミュニティに継続的に参加していることを示すが、具体的な研究内容や技術的詳細が欠如しているため、業界への直接的な影響は限定的である。主に企業の研究活動の可視化とコミュニティへの関与を示すPR的な性格が強い。
編集コメント
具体的な研究内容や技術的革新性に関する情報がなく、主にイベント参加告知の性格が強いため、実質的な技術ニュースとしては軽微な情報に留まる。
Apple silicon 上での MLX を用いたローカル LLM 推論 (Local LLM inference)
本デモでは、Apple の Apple silicon 専用オープンソース配列フレームワークである MLX を用い、MacBook Pro with M5 Max 上でオンデバイス LLM 推論 (on-device LLM inference) を紹介する。Xcode のネイティブ開発環境内で、量子化された (quantized) 最先端コーディングモデルを完全にローカルで実行する。MLX、mlx-lm、モデル重みを含むフルスタック (full stack) はオープンソースであり、研究コミュニティがこれらの手法を独自に構築・拡張することを促す。
SHARP
本デモでは、事前に録画された画像のセット、またはデモ中にユーザーが直接撮影した画像に対して SHARP を実行する様子を示す。訪問者は、画像の選択から SHARP による処理、iPad Pro with M5 chip 上で生成された3次元ガウス点群 (3D Gaussian point cloud) の表示に至る高速なプロセスを体験できる。
MLX および SHARP のデモは、展示時間の間、Apple Booth で公開される。
Carl Vondrick は ICLR 2026 の General Chair（総責任者）である。
Alexander Toshev と Vladlen Koltun は Senior Area Chairs（上級領域責任者）である。
Carl Vondrick、Eugene Ndiaye、Fartash Faghri、Jiatao Gu、Joao Monteiro、Miguel Angel Bautista、Philipp Krähenbühl、Pierre Ablin、Shuangfei Zhai、Yizhe Zhang、Zhe Gan は Area Chairs（領域責任者）である。
Arno Blaas は Workshop Co-Organizer（ワークショップ共同主催者）であり、Nicholas Apostoloff と Niv Sivakumar は「I Can’t Believe It’s Not Better: Challenges in Applied Deep Learning (ICBINB) 2026」の Workshop Reviewers（ワークショップ査読者）である。
Shirley Zou は「AI with Recursive Self-Improvement 2026」の Workshop Co-Organizer（ワークショップ共同主催者）である。
Adam Golinski、Anastasasiia Filippova、Andrew Silva、Andrew Szot、Arnav Kundu、Arno Blaas、Artem Sevastopolsky、Arwen Bradley、Barry-John Theobald、Chen Chen、Cheng-Yu Hsieh、Devon Hjelm、Gregor Bachmann、Honor Chen、Luca Zappella、Manjot Bilkhu、Meng Cao、Michael Kirchhof、Miguel Sarabia、Mohamad Shahbazi、Nicholas Apostoloff、Nikhil Bhendawade、Nivedha Sivakumar、Noam Elata、Omar Attia、Parth Thakkar、Parshin Shojaee、Peter Grasch、Ping Wang、Ran Liu、Raviteja Vemulapalli、Richard Bai、Roy Xie、Vikramjit Mitra、Vimal Thilak、Zijin Gu は Reviewers（査読者）である。
メインカンファレンスペーパー
著者Silin Gao**, Antoine Bosselut†, Samy Bengio, Emmanuel Abbe
著者Ming Gui†‡*, Johannes Schusterbauer†‡*, Timy Phan†‡, Felix Krause†‡, Josh Susskind, Miguel Angel Bautista, Björn Ommer†‡
著者Deepro Choudhury†, Sinead Williamson, Adam Goliński, Ning Miao‡, Freddie Bickford Smith†, Michael Kirchhof, Yizhe Zhang, Tom Rainforth†
著者Amir Joudaki†, Giulia Lanzillotta†, Mohammad Samragh Razlighi, Iman Mirzadeh, Keivan Alizadeh, Thomas Hofmann†, Mehrdad Farajtabar, Fartash Faghri
著者Santiago Cuervo†, Skyler Seto, Maureen de Seyssel, Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly, Zakaria Aldeneh
著者Bruno Mlodozeniec†**, Pierre Ablin, Louis Béthune, Dan Busbridge, Michal Klein, Jason Ramapuram, Marco Cuturi
著者Aleksandr Dremov**†, David Grangier, Angelos Katharopoulos, Awni Hannun
著者Huangjie Zheng, Shansan Gong‡, Ruixiang Zhang, Tianrong Chen, Jiatao Gu,, Mingyuan Zhou†, Navdeep Jaitly, Yizhe Zhang
著者Vishaal Udandarao†‡, Zhiyun Lu, Xuankai Chang, Yongqiang Wang, Violet Z. Yao, Albin Madapally Jose, Fartash Faghri, Josh Gardner, Chung-Cheng Chiu
著者Shansan Gong†, Ruixiang Zhang, Huangjie Zheng, Jiatao Gu, Navdeep Jaitly, Lingpeng Kong†, Yizhe Zhang
著者Ryan Hoque*, Peide Huang*, David J. Yoon*, Mouli Sivapurapu, Jian Zhang
著者Wenhui Cui†**, Christopher M. Sandino, Hadi Pouransar, Ran Liu, Juri Minxha, Ellen L. Zippi, Erdrin Azemi, Behrooz Mahasseni
著者Aleksei Petrenko‡, Ben Lipkin†‡**, Kevin Chen, Erik Wijmans, Marco Cusumano-Towner, Raja Giryes, Philipp Krähenbühl
著者Stephen Zhang, Seyed Alireza Mousavi Hosseini, Michal Klein, Marco Cuturi
著者Amin Karimi Monsefi†‡, Nikhil Bhendawade, Manuel R. Ciosici, Dominic Culver, Yizhe Zhang, Irina Belousova
著者Emily Cheng†, Carmen Amo Alonso‡, Federico Danieli, Arno Blaas, Luca Zappella, Pau Rodríguez, Xavier Suau
著者Silvia Sapora**, Devon Hjelm, Alexander Toshev, Omar Attia, Bogdan Mazoure
著者Sumanth Varambally**†, Thomas Voice, Yanchao Sun, Zhifeng Chen, Rose Yu†, Ke Ye
LaDiR：Latent Diffusion（潜在拡散モデル）がLLMs（大規模言語モデル）のテキスト推論を強化するMurray Kang (UCSD), Yizhe Zhang, Nikki Kuang (UCSD), Nicklas Majamaki (UCSD), Navdeep Jaitly, Yian Ma (UCSD), Lianhui Qin (UCSD)
適応的長さベースの報酬整形（Adaptive Length-based Reward Shaping）による効率的な推論学習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)
著者Shenao Zhang†, Donghan Yu, Yihao Feng, Bowen Jin‡, Zhaoran Wang†, John Peebles**, Zirui Wang
著者Hsuan Su†, Ting-Yao Hu, Hema Swetha Koppula, Kundan Krishna, Hadi Pouransari, Cheng-Yu Hsieh, Cem Koc, Joseph Yitan Cheng, Oncel Tuzel, Raviteja Vemulapalli
著者Yixing Lao†**, Xuyang Bai, Xiaoyang Wu†, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao†
著者Jen-Hao Rick Chang‡, Xiaoming Zhao‡, Dorian Chan, Oncel Tuzel
著者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
著者Fartash Faghri*, Pavan Kumar Anasossalu Vasu*, Cem Koc, Vaishaal Shankar†, Alexander Toshev, Oncel Tuzel, Hadi Pouransari
著者Sarah Ball†, Greg Gluch‡, Shafi Goldwasser‡, Frauke Kreuter†§, Omer Reingold¶, Guy N. Rothblum
著者Federico Danieli, Pau Rodriguez, Miguel Sarabia, Xavier Suau, Luca Zappella
著者Hadi Pouransari, David Grangier, C Thomas, Michael Kirchhof, Oncel Tuzel
著者Xianhang Li†, Chen Huang, Chun-Liang Li, Eran Malach, Josh Susskind, Vimal Thilak, Etai Littwin
著者Alex Fang†, Thomas Voice, Ruoming Pang, Ludwig Schmidt†, Tom Gunter**
著者Jakub Krajewski**, Amitis Shidani, Dan Busbridge, Sam Wiseman, Jason Ramapuram
著者Mohammad Hossein Amani†, Aryo Lotfi†, Nicolas Mario Baldwin†, Samy Bengio, Mehrdad Farajtabar, Emmanuel Abbé*, Robert West*†
著者Ram Ramrakhya**, Andrew Szot, Omar Attia, Yuhao Yang, Anh Nguyen, Bogdan Mazoure, Zhe Gan, Harsh Agrawal, Alexander Toshev
著者Michael Kirchhoff, Luca Füger†, Adam Goliński, Eeshan Gunesh Dhekane, Arno Blaas, Seong Joon Oh‡, Sinead Williamson
著者Angie Boggust†, Donghao Ren, Yannick Assogba, Dominik Moritz, Arvind Satyanarayan†, Fred Hohman
著者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
著者Yuyang Wang, Jiarui Lu**, Navdeep Jaitly, Josh Susskind, Miguel Angel Bautista
著者Zitong Yang†‡, Aonan Zhang‡, Hong Liu†, Tatsunori Hashimoto†, Emmanuel Candès†, Chong Wang, Ruoming Pang
著者Gregor Bachmann, Yichen Jiang, Seyed Mohsen Moosavi Dezfooli, Moin Nabi
著者Eran Malach, Omid Saremi, Sinead Williamson, Arwen Bradley, Aryo Lotfi, Emmanuel Abbe, Josh Susskind, Etai Littwin
著者Preetum Nakkiran, Arwen Bradley, Adam Goliński, Eugene Ndiaye, Michael Kirchhof, Sinead Williamson
著者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
著者：Jiayuan Ye、Vitaly Feldman、Kunal Talwar 著者：Kundan Krishna、Joseph Y Cheng、Charles Maalouf、Leon A Gatys 著者：Szilvia Ujváry†、Louis Béthune、Pierre Ablin、João Monteiro、Marco Cuturi、Michael Kirchhof 著者：Bingbing Wen、Sirajul Salekin、Feiyang Kang†、Lucy Lu Wang‡、Bill Howe‡、Javier Movellan、Manjot Bilkhu 時系列にわたる時間の物語（NoTS）Wenrui Ma（University of Pennsylvania）、Ran Liu、Ellen Zippi、Chris Sandino、Juri Minxha、Behrooz Mahasseni、Erdrin Azemi、Ali Moin、Eva Dyer（University of Pennsylvania） 著者：Skyler Seto、Pierre Ablin、Anastasiia Filippova、Jiayuan Ye†、Louis Béthune、Angelos Katharopoulos、David Grangier 著者：Alec Helbling†、Shruti Palaskar、Kundan Krishna、Polo Chau†、Leon Gatys‡、Joseph Yitan Cheng‡ 著者：Lorenzo Noci、Gregor Bachmann、Seyed-Mohsen Moosavi-Dezfooli、Moin Nabi 記憶を深度と交換する：キャッシュ制約に対する大規模言語モデル（LLMs）の堅牢化Joao Monteiro、Anastasiia Filippova、David Grangier、Marco Cuturi 関連資料と更新情報。Appleは、12月2日から7日にカリフォルニア州サンディエゴで開催される年次ニューラル情報処理システム学会（NeurIPS）において、新たな研究を発表しています。当社は、機械学習（Machine Learning）をめぐる学術界と産業界の研究者を一堂に集める多トラックの学際的会議のスポンサーを再び務められることを誇りに思います。以下は、NeurIPS 2025におけるAppleの参加概要です。 続きを読む AppleはInternational Conference on Learning Representations（ICLR）のスポンサーを務めました。本会議は4月25日から29日までオンラインで開催されました。ICLRは、ディープラーニング（deep learning）の発展に貢献する専門家の集いであります。 続きを読む
原文を表示
content type eventpublished April 17, 2026Apple is presenting new research at the annual International Conference on Learning Representations (ICLR), which takes place in person in Rio de Janeiro, Brazil, from April 23 to 27. We are proud to again sponsor the conference, which brings together the scientific and industrial research communities focused on deep learning. Below is an overview of Apple’s participation at ICLR 2026:
Jump to a section:
Schedule
Technical Demos
Acknowledgements
Main Conference Papers
Workshop Papers
Stop by the Apple booth #204 during exhibition hours: 9:30 AM - 5:30 PM (Thursday, April 23 - Saturday, April 25). All times referenced in schedule are in BRT (local time).
ScheduleThursday, April 23POSTERPretraining with Hierarchical Memories: Separating Long-Tail and Common Knowledge10:30 AM - 1:00 PM, Poster Session 1, Pavilion 3, #0309Hadi Pour Ansari, C Thomas, David Grangier, Michael Kirchhof, Oncel TuzelPOSTERThe Potential of CoT for Reasoning: A Closer Look at Trace Dynamics
10:30 AM - 1:00 PM, Poster Session 1, Pavilion 4, #4708Gregor Bachmann, Yichen Jiang, Seyed Mohsen Moosavi Dezfooli, Moin NabiPOSTERRevisiting the Scaling Properties of Downstream Metrics in Large Language Model Training10:30 AM - 1:00 PM, Poster Session 1, Pavilion 4, #5008 Jakub Krajewski, Dan Busbridge, Amitis Shidani, Sam Wiseman, Jason RamapuramPOSTERSynthetic Bootstrapped Pretraining
10:30 AM - 1:00 PM, Poster Session 1, Pavilion 4, #5204Zitong Yang (Stanford University), Aonan Zhang, Hong Liu (Stanford University), Emmanuel Candès (Stanford University), Tatsunori Hashimoto (Stanford University), Chong Wang, Ruoming PangPOSTERSelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
3:15 PM - 5:45 PM, Poster Session 2, Pavilion 3, #0312Michael Kirchhof, Luca Füger (Independent Researcher), Adam Golinski, Eeshan Gunesh Dhekane, Arno Blaas, Seong Joon Oh (Tübingen AI Center), Sinead WilliamsonPOSTERFlow Matching with Semidiscrete Couplings3:15 PM - 5:45 PM, Poster Session 2, Pavilion 3, #0812Stephen Zhang (University of Melbourne), Seyed Alireza Mousavi Hosseini (University of Toronto), Michal Klein, Marco CuturiPOSTERGenCtrl — A Formal Controllability Toolkit for Generative Models3:15 PM - 5:45 PM, Poster Session 2, Pavilion 3, #0922Emily Cheng (Universitat Pompeu Fabra), Carmen Amo Alonso (Stanford University), Federico Danieli, Arno Blaas, Luca Zappella, Pau Rodriguez, Xavier SuauPOSTERScaling Synthetic Task Generation for Agents via Exploration3:15 PM - 5:45 PM, Poster Session 2, Pavilion 3, #1719Ram Ramrakhya (Georgia Institute of Technology), Harsh Agrawal, Anh Nguyen, Omar Attia, Bogdan Mazoure, Yuhao Yang, Zhe Gan, Andrew Szot, Alexander ToshevPOSTER Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
3:15 PM - 5:45 PM, Poster Session 2, Pavilion 3, #1801Yixing Lao (The University of Hong Kong), Xuyang Bai, Xiaoyang Wu, Arnold Yan, Zixin Luo, Tian Fang, Danny Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao (The University of Hong Kong)POSTERLearn to Reason Efficiently with Adaptive Length-based Reward Shaping
3:15 PM - 5:45 PM, Poster Session 2, Pavilion 3, #1820Wei Liu (HKUST), Ruochen Zhou (HKUST), Yiyun Deng (HKUST), Yuzhen Huang (HKUST), Jaunting Liu (HLUST), Yuntian Deng (University of Waterloo), Yizhe Zhang, Junxian He (HKUST)POSTERMANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
3:15 PM - 5:45 PM, Poster Session 2, Pavilion 3, #1921Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang (Meta), Ashley 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 (Meta), Zhifeng ChenPOSTERLearning to Reason for Hallucination Span Detection3:15 PM - 5:45 PM, Poster Session 2, Pavilion 3, #1924Hsuan Su, Ting-Yao Hu, Hema Koppula, Kundan Krishna, Hadi Pour Ansari, Cheng-Yu Hsieh, Cem Koc, Joseph Yitan Cheng, Oncel Tuzel, Raviteja VemulapalliPOSTEROn the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment3:15 PM - 5:45 PM, Poster Session 2, Pavilion 4, #3902Sarah Ball (University of Munich), Greg Gluch (UC Berkeley), Shafi Goldwasser (UC Berkeley), Frauke Kreuter (University of Munich), Omer Reingold (Stanford University), Guy RothblumPOSTEREntropy-Preserving Reinforcement Learning
3:15 PM - 5:45 PM, Poster Session 2, Pavilion 4, #4708Ben Lipkin (MIT), Aleksei Petrenko, Kevin Chen, Erik Wijmans, Marco Cusumano-Towner, Raja Giryes, Philipp KrähenbühlPOSTERSimpleFold: Folding Proteins is Simpler than You Think
3:15 PM - 5:45 PM, Poster Session 2, Pavilion 4, #5308Yuyang Wang, Navdeep Jaitly, Josh Susskind, Miguel Angel BautistaFriday, April 24POSTERParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models10:30 AM - 1:00 PM, Poster Session 3, Pavilion 3, #0517 Federico Danieli, Pau Rodriguez, Miguel Sarabia, Xavier Suau, Luca ZappellaPOSTERCompute-Optimal Quantization-Aware Training10:30 AM - 1:00 PM, Poster Session 3, Pavilion 3, #0524Alex Dremov (EPFL), David Grangier, Angelos Katharopoulos, Awni HannunPOSTERSharp Monocular View Synthesis in Less Than a Second
10:30 AM - 1:00 PM, Poster Session 3, Pavilion 4, #3207Lars Mescheder, Wei Dong, Shiwei Li, Xuyang Bai, Marcel Santos, Peiyun Hu, Bruno Lecouat, Mingmin Zhen, Amael Delaunoy, Tian Fang, Yanghai Tsin, Stephan Richter, Vladlen KoltunPOSTERLiTo: Surface Light Field Tokenization
10:30 AM - 1:00 PM, Poster Session 3, Pavilion 4, #3217Rick Chang, Xiaoming Zhao, Dorian Chan, Oncel TuzelPOSTERSemantic Regexes: Auto-Interpreting LLM Features with a Structured Language
10:30 AM - 1:00 PM, Poster Session 3, Pavilion 4, #4018Angie Boggust (Massachusetts Institute of Technology), Donghao Ren, Yannick Assogba, Dominik Moritz, Arvind Satyanarayan (Massachusetts Institute of Technology), Fred HohmanPOSTERVLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety
10:30 AM - 1:00 PM, Poster Session 3, Pavilion 4, #4104Shruti Palaskar, Leon Gatys, Mona Abdelrahman, Mar Jacobo, Larry Lindsey, Rutika Moharir, Gunnar Lund, Yang Xu, Navid Shiee, Jeffrey Bigham, Charlie Maalouf, Joseph Yitan ChengPOSTERAbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking10:30 AM - 1:00 PM, Poster Session 3, Pavilion 4, #4615Silin Gao (EPFL), Antoine Bosselut (EPFL), Samy Bengio, Emmanuel AbbePOSTERRL for Reasoning by Adaptively Revealing Rationales10:30 AM - 1:00 PM, Poster Session 3, Pavilion 4, #4910Mohammad Hossein Amani (EPFL), Aryo Lotfi, Nicolas Baldwin (EPFL), Samy Bengio, Mehrdad Farajtabar, Emmanuel Abbe, Robert West (EPFL)POSTERLaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
10:30 AM - 1:00 PM, Poster Session 3, Pavilion 4, #4916Murray Kang (UCSD), Yizhe Zhang, Nikki Kuang (UCSD), Nicklas Majamaki (UCSD), Navdeep Jaitly, Yian Ma (UCSD), Lianhui Qin (UCSD)POSTERCompleted Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration3:15 PM - 5:45 PM, Poster Session 4, Pavilion 3, #0403Bruno Kacper Mlodozeniec (University of Cambridge), Pierre Ablin, Louis Béthune, Dan Busbridge, Michal Klein, Jason Ramapuram, Marco CuturiPOSTERContinuously Augmented Discrete Diffusion model for Categorical Generative Modeling
3:15 PM - 5:45 PM, Poster Session 4, Pavilion 3, #0723Huangjie Zheng, Shansan Gong, Tianrong Chen, Ruixiang Zhang, Jiatao Gu, Mingyuan Zhou (University of Texas), Navdeep Jaitly, Yizhe ZhangPOSTERReusing Pre-Training Data at Test Time is a Compute Multiplier3:15 PM - 5:45 PM, Poster Session 4, Pavilion 3, #1025Alex Fang (Stanford), Thomas Voice, Ruoming Pang, Ludwig Schmidt (Stanford), Tom GunterPOSTEREgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
3:15 PM - 5:45 PM, Poster Session 4, Pavilion 3, #1305Ryan Hoque, Peide Huang, David Yoon, Mouli Sivapurapu, Jian ZhangPOSTEREMBridge: Enhancing Gesture Generalization from EMG Signals Through Cross-modal Representation Learning
3:15 PM - 5:45 PM, Poster Session 4, Pavilion 3, #1319Behrooz Mahasseni, Wenhui Cui (USC), Erdrin Azemi, Chris Sandino, Juri Minxha, Ellen Zippi, Hadi Pour AnsariPOSTER Closing the Gap Between Text and Speech Understanding in LLMs
3:15 PM - 5:45 PM, Poster Session 4, Pavilion 3, #1401Santiago Cuervo, Skyler Seto, Maureen de Seyssel, Richard Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly, Zak AldenehPOSTERAdaptive Thinking: Large Language Models Know When to Think in Latent Space
3:15 PM - 5:45 PM, Poster Session 4, Pavilion 3, #2009Pingzhi Li (University of North Carolina, Chapel Hill), Bairu Hou (University of California, Santa Barbara), Yun Zhu, Yihao Feng, Ke Ye, Tao Lei, Zhifeng Chen, Tianlong Chen (University of North Carolina, Chapel Hill), Xianzhi DuPOSTERBED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design3:15 PM - 5:45 PM, Poster Session 4, Pavilion 4, #4412Deepro Choudhury (University of Oxford), Sinead Williamson, Michael Kirchhof, Adam Golinski, Yizhe Zhang, Ning Miao (City University of Hong Kong), Freddie Bickford Smith (University of Oxford), Tom Rainforth (University of Oxford)ORALParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models3:51 PM - 4:01 PM, Oral Session 4A ML Architectures and Training II, AmphitheaterFederico Danieli, Pau Rodriguez, Miguel Sarabia, Xavier Suau, Luca ZappellaSaturday, April 25POSTERAdapting Self-Supervised Representations as a Latent Space for Efficient Generation10:30 AM - 1:00 PM, Poster Session 5, Pavilion 3, #0824Ming Gui (LMU), Johannes Schusterbauer (LMU), Timy Phan (LMU), Felix Krause (LMU), Josh Susskind, Miguel Angel Bautista, Björn Ommer (LMU)POSTERMobileCLIP2: Improving Multi-Modal Reinforced Training10:30 AM - 1:00 PM, Poster Session 5, Pavilion 4, #3713Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar (work done while at Apple), Alexander Toshev, Oncel Tuzel, Hadi Pour Ansari
POSTERTrained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs10:30 AM - 1:00 PM, Poster Session 5, Pavilion 4, #4411Preetum Nakkiran, Arwen Bradley, Adam Golinski, Michael Kirchhof, Eugene Ndiaye, Sinead WilliamsonPOSTERLearning to Reason as Action Abstractions with Scalable Mid-Training RL10:30 AM - 1:00 PM, Poster Session 5, Pavilion 4, #4507Shenao Zhang (Northwestern University), Donghan Yu, Yihao Feng, Bowen Jin (University of Illinois Urbana-Champaign), Zhaoran Wang (Northwestern University), John Peebles, Zirui WangPOSTERDiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
10:30 AM - 1:00 PM, Poster Session 5, Pavilion 4, #5213Shansan Gong (HKU), Ruixiang Zhang, Huangjie Zheng, Navdeep Jaitly, Lingpeng Kong (HKU), Yizhe Zhang, Jiatao GuORALTo Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models
11:18 AM - 11:28 AM, Oral Session 5C Reinforcement learning II, 202 A/BEran Malach, Omid Saremi, Sinead Williamson, Arwen Bradley, Aryo Lotfi, Emmanuel Abbe, Josh Susskind, Etai LittwinEXPO TALKParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models12:00 PM - 1:00 PM, 205Federico Danieli will be giving the Apple Expo Talk at ICLR 2026.POSTER Rethinking JEPA: Compute‑Efficient Video SSL with Frozen Teachers3:15 PM - 5:45 PM, Poster Session 6, Pavilion 3, #0211Xianhang Li (UCSC), Chen Huang, Chun-Liang Li, Eran Malach, Josh Susskind, Vimal Thilak, Etai LittwinPOSTERHilbert: Recursively Building Formal Proofs with Informal Reasoning3:15 PM - 5:45 PM, Poster Session 6, Pavilion 3, #0516Sumanth Varambally (UCSD), Thomas Voice, Yanchao Sun, Zhifeng Chen, Rose Yu (UCSD), Ke YePOSTERFS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models3:15 PM - 5:45 PM, Poster Session 6, Pavilion 3, #0618Amin Karimi Monsefi (The Ohio State University), Nikhil Bhendawade, Manuel Ciosici, Yizhe Zhang, Irina BelousovaPOSTERData-Centric Lessons To Improve Speech-Language Pretraining
3:15 PM - 5:45 PM, Poster Session 6, Pavilion 3, #1418Vishaal Udandarao, Zhiyun Lu, Yongqiang Wang, Albin Madappally Jose, Fartash Faghri, Xuankai Chang, Chung-Cheng Chiu, Joshua P. GardnerPOSTERBarriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity3:15 PM - 5:45 PM, Poster Session 6, Pavilion 4, #4202Amir Joudaki (ETH Zurich), Giulia Lanzillotta (ETH Zurich), Mohammad Samragh Razlighi, Iman Mirzadeh, Keivan Alizadeh Vahid, Thomas Hofmann (ETH Zurich), Mehrdad Farajtabar, Fartash FaghriPOSTERGRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning
3:15 PM - 5:45 PM, Poster Session 6, Pavilion 4, #4602Silvia Sapora (Oxford), Devon Hjelm, Alexander Toshev, Omar Attia, Bogdan MazoureSunday, April 26WORKSHOPNarrative of Time Across Scales (NoTS) 9:00 AM - 5:00 PM, Time Series in the Age of Large Models Workshop 2026, 205Wenrui Ma (University of Pennsylvania), Ran Liu, Ellen Zippi, Chris Sandino, Juri Minxha, Behrooz Mahasseni, Erdrin Azemi, Ali Moin, Eva Dyer (University of Pennsylvania)WORKSHOP MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining9:00 AM - 5:00 PM, Workshop on Navigating and Addressing Data Problems for Foundation Models 2026, 203 A/BBingbing Wen (University of Washington), Sirajul Salekin, Feiyang Kang (Virginia Institute of Technology), Lucy Lu Wang (University of Washington), Bill Howe (University of Washington), Javier Movellan, Manjot BilkhuWORKSHOPCram Less to Fit More: Training Data Pruning Improves Memorization of Facts9:00 AM - 5:00 PM, Workshop on Navigating and Addressing Data Problems for Foundation Models 2026, 203 A/BJiayuan Ye (National University of Singapore), Vitaly Feldman, Kunal TalwarWORKSHOPOptimal Splitting of Language Models from Mixtures to Specialized Domains9:00 AM - 5:00 PM, Workshop on Navigating and Addressing Data Problems for Foundation Models 2026, 203 A/BSkyler Seto, Pierre Ablin, Anastasiia Filippova, Jiayuan Ye (National University of Singapore), Louis Béthune, Angelos Katharopoulos, David GrangierMonday, April 27WORKSHOPTrading Depth for Memory: Robustifying LLMs against Cache Constraints9:00 AM - 5:00 PM, 3rd Workshop on Test-Time Updates (TTU): Putting Updates to the Test! 2026, 206Joao Monteiro, Anastasiia Filippova, David Grangier, Marco CuturiWORKSHOPDisentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
9:00 AM - 5:00 PM, Principled Design for Trustworthy AI - Interpretability, Robustness, and Safety across Modalities 2026, 204 A/BKundan Krishna, Joseph Yitan Cheng, Charlie Maalouf, Leon Gatys
WORKSHOPSafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation9:00 AM - 5:00 PM, Principled Design for Trustworthy AI - Interpretability, Robustness, and Safety across Modalities 2026, 204 A/BAlec Helbling (Georgia Institute of Technology), Shruti Palaskar, Kundan Krishna, Polo Chau, Leon Gatys, Joseph Yitan ChengWORKSHOPThinking into the Future: Latent Lookahead Training for Transformers9:00 AM - 5:00 PM, Workshop on Latent & Implicit Thinking – Going Beyond CoT Reasoning 2026, 101 ALorenzo Noci (ETH Zurich), Moin Nabi, Gregor Bachmann, Seyed Mohsen Moosavi DezfooliWORKSHOPLaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss9:00 AM - 5:00 PM, Workshop on Memory for LLM-Based Agentic Systems 2026, 205Szilvia Reka Ujvary, Michael Kirchhof, Louis Béthune, Marco Cuturi, Pierre Ablin, Joao MonteiroWORKSHOP INVITED TALKLatent & Implicit Thinking – Going Beyond CoT Reasoning 202611:10 AM - 11:40 AM, 101 ASamy Bengio will be giving the Keynote Talk 3 at the Workshop.WORKSHOP PANELIST DISCUSSIONI Can't Believe It's Not Better: Where Large Language Models Need to Improve 20264:05 PM - 4:55 PM, 201 CSamy Bengio will participate in an invited Panelist Discussion at the workshop.
Local LLM inference on Apple silicon with MLX
This demo will showcase on-device LLM inference on a MacBook Pro with M5 Max using MLX, Apple’s open-source array framework purpose-built for Apple silicon, running a quantized frontier coding model entirely locally within Xcode’s native development environment. The full stack — MLX, mlx-lm, and model weights — is open source, inviting the research community to build on and extend these methods independently.
SHARP
This demo shows SHARP running on a set of pre-recorded images or images captured directly by the user during the demo. Visitors will experience the fast process from selecting an image, processing it with SHARP, and viewing the generated 3D Gaussian point cloud on an iPad Pro with the M5 chip.
Both MLX and SHARP demos will be available at the Apple Booth during exhibition hours.
Carl Vondrick is the ICLR 2026 General Chair.
Alexander Toshev and Vladlen Koltun are Senior Area Chairs.
Carl Vondrick, Eugene Ndiaye, Fartash Faghri, Jiatao Gu, Joao Monteiro, Miguel Angel Bautista, Philipp Krähenbühl, Pierre Ablin, Shuangfei Zhai, and Yizhe Zhang, and Zhe Gan are Area Chairs.
Arno Blaas is a Workshop Co-Organizer, and Nicholas Apostoloff and Niv Sivakumar are Workshop Reviewers for “I Can’t Believe It’s Not Better: Challenges in Applied Deep Learning (ICBINB) 2026.”
Shirley Zou is a Workshop Co-Organizer for “AI with Recursive Self-Improvement 2026.”
Adam Golinski, Anastasasiia Filippova, Andrew Silva, Andrew Szot, Arnav Kundu, Arno Blaas, Artem Sevastopolsky, Arwen Bradley, Barry-John Theobald, Chen Chen, Cheng-Yu Hsieh, Devon Hjelm, Gregor Bachmann, Honor Chen, Luca Zappella, Manjot Bilkhu, Meng Cao, Michael Kirchhof, Miguel Sarabia, Mohamad Shahbazi, Nicholas Apostoloff, Nikhil Bhendawade, Nivedha Sivakumar, Noam Elata, Omar Attia, Parth Thakkar, Parshin Shojaee, Peter Grasch, Ping Wang, Ran Liu, Raviteja Vemulapalli, Richard Bai, Roy Xie, Vikramjit Mitra, Vimal Thilak, and Zijin Gu are Reviewers.
Main Conference Papers
AuthorsSilin Gao, Antoine Bosselut†, Samy Bengio, Emmanuel AbbeAuthorsMing Gui†‡*, Johannes Schusterbauer†‡*, Timy Phan†‡, Felix Krause†‡, Josh Susskind, Miguel Angel Bautista, Björn Ommer†‡AuthorsDeepro Choudhury†, Sinead Williamson, Adam Goliński, Ning Miao‡, Freddie Bickford Smith†, Michael Kirchhof, Yizhe Zhang, Tom Rainforth†AuthorsAmir Joudaki†, Giulia Lanzillotta†, Mohammad Samragh Razlighi, Iman Mirzadeh, Keivan Alizadeh, Thomas Hofmann†, Mehrdad Farajtabar, Fartash FaghriAuthorsSantiago Cuervo†, Skyler Seto, Maureen de Seyssel, Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly, Zakaria AldenehAuthorsBruno Mlodozeniec†, Pierre Ablin, Louis Béthune, Dan Busbridge, Michal Klein, Jason Ramapuram, Marco CuturiAuthorsAleksandr Dremov†, David Grangier, Angelos Katharopoulos, Awni HannunAuthorsHuangjie Zheng, Shansan Gong‡, Ruixiang Zhang, Tianrong Chen, Jiatao Gu,, Mingyuan Zhou†, Navdeep Jaitly, Yizhe ZhangAuthorsVishaal Udandarao†‡, Zhiyun Lu, Xuankai Chang, Yongqiang Wang, Violet Z. Yao, Albin Madapally Jose, Fartash Faghri, Josh Gardner, Chung-Cheng ChiuAuthorsShansan Gong†, Ruixiang Zhang, Huangjie Zheng, Jiatao Gu, Navdeep Jaitly, Lingpeng Kong†, Yizhe ZhangAuthorsRyan Hoque*, Peide Huang*, David J. Yoon*, Mouli Sivapurapu, Jian ZhangAuthorsWenhui Cui†, Christopher M. Sandino, Hadi Pouransar, Ran Liu, Juri Minxha, Ellen L. Zippi, Erdrin Azemi, Behrooz MahasseniAuthorsAleksei Petrenko‡, Ben Lipkin†‡, Kevin Chen, Erik Wijmans, Marco Cusumano-Towner, Raja Giryes, Philipp KrähenbühlAuthorsStephen Zhang, Seyed Alireza Mousavi Hosseini, Michal Klein, Marco CuturiAuthorsAmin Karimi Monsefi†‡, Nikhil Bhendawade, Manuel R. Ciosici, Dominic Culver, Yizhe Zhang, Irina BelousovaAuthorsEmily Cheng†, Carmen Amo Alonso‡, Federico Danieli, Arno Blaas, Luca Zappella, Pau Rodríguez, Xavier SuauAuthorsSilvia Sapora, Devon Hjelm, Alexander Toshev, Omar Attia, Bogdan MazoureAuthorsSumanth Varambally†, Thomas Voice, Yanchao Sun, Zhifeng Chen, Rose Yu†, Ke YeLaDiR: Latent Diffusion Enhances LLMs for Text ReasoningMurray 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 ShapingWei Liu (HKUST), Ruochen Zhou (HKUST), Yiyun Deng (HKUST), Yuzhen Huang (HKUST), Jaunting Liu (HLUST), Yuntian Deng (University of Waterloo), Yizhe Zhang, Junxian He (HKUST)AuthorsShenao Zhang†, Donghan Yu, Yihao Feng, Bowen Jin‡, Zhaoran Wang†, John Peebles, Zirui WangAuthorsHsuan Su†, Ting-Yao Hu, Hema Swetha Koppula, Kundan Krishna, Hadi Pouransari, Cheng-Yu Hsieh, Cem Koc, Joseph Yitan Cheng, Oncel Tuzel, Raviteja VemulapalliAuthorsYixing Lao†, Xuyang Bai, Xiaoyang Wu†, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Shiwei Li, Hengshuang Zhao†AuthorsJen-Hao Rick Chang‡, Xiaoming Zhao‡, Dorian Chan, Oncel TuzelAuthorsYanghao 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 ChenAuthorsFartash Faghri*, Pavan Kumar Anasossalu Vasu*, Cem Koc, Vaishaal Shankar†, Alexander Toshev, Oncel Tuzel, Hadi PouransariAuthorsSarah Ball†, Greg Gluch‡, Shafi Goldwasser‡, Frauke Kreuter†§, Omer Reingold¶, Guy N. RothblumAuthorsFederico Danieli, Pau Rodriguez, Miguel Sarabia, Xavier Suau, Luca ZappellaAuthorsHadi Pouransari, David Grangier, C Thomas, Michael Kirchhof, Oncel TuzelAuthorsXianhang Li†, Chen Huang, Chun-Liang Li, Eran Malach, Josh Susskind, Vimal Thilak, Etai LittwinAuthorsAlex Fang†, Thomas Voice, Ruoming Pang, Ludwig Schmidt†, Tom GunterAuthorsJakub Krajewski, Amitis Shidani, Dan Busbridge, Sam Wiseman, Jason RamapuramAuthorsMohammad Hossein Amani†, Aryo Lotfi†, Nicolas Mario Baldwin†, Samy Bengio, Mehrdad Farajtabar, Emmanuel Abbé*, Robert West*†AuthorsRam Ramrakhya, Andrew Szot, Omar Attia, Yuhao Yang, Anh Nguyen, Bogdan Mazoure, Zhe Gan, Harsh Agrawal, Alexander ToshevAuthorsMichael Kirchhoff, Luca Füger†, Adam Goliński, Eeshan Gunesh Dhekane, Arno Blaas, Seong Joon Oh‡, Sinead WilliamsonAuthorsAngie Boggust†, Donghao Ren, Yannick Assogba, Dominik Moritz, Arvind Satyanarayan†, Fred HohmanAuthorsLars 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 KoltunAuthorsYuyang Wang, Jiarui Lu**, Navdeep Jaitly, Josh Susskind, Miguel Angel BautistaAuthorsZitong Yang†‡, Aonan Zhang‡, Hong Liu†, Tatsunori Hashimoto†, Emmanuel Candès†, Chong Wang, Ruoming PangAuthorsGregor Bachmann, Yichen Jiang, Seyed Mohsen Moosavi Dezfooli, Moin NabiAuthorsEran Malach, Omid Saremi, Sinead Williamson, Arwen Bradley, Aryo Lotfi, Emmanuel Abbe, Josh Susskind, Etai LittwinAuthorsPreetum Nakkiran, Arwen Bradley, Adam Goliński, Eugene Ndiaye, Michael Kirchhof, Sinead WilliamsonAuthorsShruti Palaskar, Leon Gatys, Mona Abdelrahman, Mar Jacobo, Larry Lindsey, Rutika Moharir, Gunnar Lund, Yang Xu, Navid Shiee, Jeffrey Bigham, Charles Maalouf, Joseph Yitan Cheng
AuthorsJiayuan Ye, Vitaly Feldman, Kunal TalwarAuthorsKundan Krishna, Joseph Y Cheng, Charles Maalouf, Leon A GatysAuthorsSzilvia Ujváry†, Louis Béthune, Pierre Ablin, João Monteiro, Marco Cuturi, Michael KirchhofAuthorsBingbing Wen, Sirajul Salekin, Feiyang Kang†, Lucy Lu Wang‡, Bill Howe‡, Javier Movellan, Manjot BilkhuNarrative of Time Across Scales (NoTS) Wenrui Ma (University of Pennsylvania), Ran Liu, Ellen Zippi, Chris Sandino, Juri Minxha, Behrooz Mahasseni, Erdrin Azemi, Ali Moin, Eva Dyer (University of Pennsylvania)AuthorsSkyler Seto, Pierre Ablin, Anastasiia Filippova, Jiayuan Ye†, Louis Béthune, Angelos Katharopoulos, David GrangierAuthorsAlec Helbling†, Shruti Palaskar, Kundan Krishna, Polo Chau†, Leon Gatys‡, Joseph Yitan Cheng‡AuthorsLorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Moin NabiTrading Depth for Memory: Robustifying LLMs against Cache ConstraintsJoao Monteiro, Anastasiia Filippova, David Grangier, Marco CuturiRelated readings and updates.Apple is presenting new research at the annual conference on Neural Information Processing Systems (NeurIPS), which takes place in person in San Diego, California, from December 2 – 7. We are proud to again sponsor the multi-track interdisciplinary conference, which brings together the scientific and industrial research communities surrounding Machine Learning. Below is an overview of Apple’s participation at NeurIPS 2025.Read moreApple sponsored the International Conference on Learning Representations (ICLR). It was held virtually from April 25 to 29. ICLR is a gathering of professionals dedicated to the advancement of deep learning.Read more
関連記事
カーネギーメロン大学、NeurIPS 2025で156件の研究を発表
カーネギーメロン大学の研究者がNeurIPS 2025で156件の論文を発表。神経情報処理分野の最新研究を紹介し、AI技術の発展に貢献。
セキュアなガバナンスが金融AIの収益成長を加速
金融機関は、収益成長と市場優位性のためにコンプライアントなAIソリューションを展開することを学んでいる。従来は効率向上の手段と見なされていたが、現在はガバナンスを重視したAI導入が進展している。
AAAI-2026 参加報告：サイバーエージェント村田氏がシンガポールで開催された人工知能国際会議に参加し、採択論文を発表
サイバーエージェントの AI チーム所属・村田氏は、1 月 20 日から 27 日にシンガポールで開催された人工知能研究の国際会議「AAAI-2026」に参加しました。同氏は学生時代から継続していた論文が採択され、過去最多の投稿数があった本会議で研究成果を発表しました。