ICLR: International Conference on Learning Representations

ICLR est l'une des principales conférences sur l'apprentissage profond et l'apprentissage de représentations. Elle présente des recherches significatives liées à la robotique, y compris l'apprentissage par renforcement pour le contrôle robotique, le transfert simulation-réalité, l'apprentissage robotique à partir de démonstrations et l'IA incarnée. La conférence réunit des chercheurs en apprentissage automatique, IA et robotique pour faire progresser l'état de l'art en représentations apprises et leurs applications.

Organisateur: ICLR
Fondée: 2013
Fréquence: Annual
A lieu généralement en: April-May
Durée: 5 days
Participation habituelle: 5000+
Public: Researchers, Engineers, Students
Thèmes: deep learning, representation learning, reinforcement learning, robot learning, sim-to-real, embodied AI, neural networks, generative models
Mots-clés: machine-learning, deep-learning, robotics, ai, reinforcement-learning

Prochaine édition

ICLR 2027, 26–30 avr. 2027, San Francisco, CA, USA

Conférenciers invités

Maja Matarić (University of Southern California; Google DeepMind): The Challenges of Human-Centered AI and Robotics: What We Want, Need, and are Getting From Human-Machine Interaction
Max Welling (University of Amsterdam; CuspAI): From Physics to AI to Materials; A Journey from Foundations to Impact
Percy Liang (Stanford University): Marin: Open Development of Frontier AI
Katie Bouman (California Institute of Technology): Images of the Hidden Universe
Karen Adolph (New York University): Learning while developing: How infants acquire intelligent behavior
Pablo Arbeláez (Universidad de los Andes (CinfonIA)): Artificial Intelligence for Open Science

Ateliers

ICLR 2026 Workshop on AI with Recursive Self-Improvement, Sunday April 26: IA à auto-amélioration récursive à travers les modèles omni, les agents multimodaux, la robotique et la découverte scientifique — reliant le post-entraînement, la recherche évolutive et les agents auto-évolutifs.
ICLR 2026 Workshop on Lifelong Agents: Learning, Aligning, Evolving, Sunday April 26: Reliant l'apprentissage continu, l'apprentissage par renforcement et l'alignement pour développer des agents IA capables d'apprendre en continu, de s'aligner sur les préférences humaines et d'évoluer de façon responsable.
ICLR 2026 Workshop on Memory for LLM-Based Agentic Systems (MemAgents), Monday April 27: Conception de la couche mémoire pour les systèmes agentiques — mémoire épisodique, sémantique, de travail et paramétrique, pipelines de récupération et benchmarks d'agents à long terme en robotique, automatisation web et maintenance logicielle.
ICLR 2026 the 2nd Workshop on World Models: Understanding, Modelling and Scaling, Monday April 27: Cadres évolutifs unifiant la modélisation générative, la prise de décision séquentielle, l'apprentissage multimodal et le raisonnement causal — avec études de cas en robotique et post-mortems d'échecs axés sur la reproductibilité.

Articles

Orthogonal Gradient Projection for Continual LLM Unlearning: Juan Belieni, Ana Carolina Erthal, Eliezer de Souza da Silva, Diego Mesquita · ICLR 2026 Workshop RSI ShortPaper · 2026
Just Enough Learning: GRPO-Guided Controllers for Hyperparameter Sweeps: Justin H Lee, Henry Ndubuaku · ICLR 2026 Workshop RSI Poster · 2026
Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants: Alejandro Breen Herrera, Aayush Sheth, Steven Guanxing Xu, Zhucheng Zhan, Charles Wright, Hong Tai Wei, Marcus Yearwood, Sudeep Das, Danny Nightingale, Meg Watson, Charles Pollnow V · ICLR 2026 Workshop RSI ShortPaper · 2026
Verifying the Verifiers: Failure Attribution for Agentic Benchmark Diagnostics and Training Data Curation: Jesse Hu, Pratyush Shukla, Ke Huang · ICLR 2026 Workshop RSI Poster · 2026
Self-Adapting Agents for Automating Research Coding Workflows: Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan · ICLR 2026 Workshop RSI Poster · 2026
Self-Improvement via Fast Tree-search: Xinghong Fu, Aravinth Kulanthaivelu, Yutaro Yamada · ICLR 2026 Workshop RSI Poster · 2026
Structure Enables Effective Self-Localization of Errors in LLMs: Ankur Samanta, Akshayaa Magesh, Ayush Jain, Kavosh Asadi, Youliang Yu, Daniel Jiang, Boris Vidolov, Kaveh Hassani, Paul Sajda, Jalaj Bhandari, Yonathan Efroni · ICLR 2026 Workshop RSI Poster · 2026
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement: Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary · ICLR 2026 Workshop RSI Poster · 2026
Adaptive Meta-Curriculum for Test-Time Self-Improvement: Kaustubh S. Bukkapatnam, Aarav Lala, Laksh Patel · ICLR 2026 Workshop RSI Spotlight · 2026
GASP: Guided Asymmetric Self-Play For Coding LLMs: Swadesh Jana, Cansu Sancaktar, Tomáš Daniš, Georg Martius, Antonio Orvieto, Pavel Kolev · ICLR 2026 Workshop RSI Spotlight · 2026
Interestingness as an Inductive Heuristic for Future Compression Progress: Vincent Herrmann, Jürgen Schmidhuber · ICLR 2026 Workshop RSI Spotlight · 2026
In-Context Adaptation: Yongqiang Chen, Chenxi Liu, Qingyi Guo, Bo Han, Kun Zhang · ICLR 2026 Workshop RSI Poster · 2026
Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement: Taegu Kang, Jaesik Yoon, Sungjin Ahn · ICLR 2026 Workshop RSI Poster · 2026
Anchored Self-Play for Code Repair: Caroline Choi, Zeyneb N. Kaya, Shirley Wu, Tengyu Ma, Tatsunori Hashimoto, Ludwig Schmidt · ICLR 2026 Workshop RSI Spotlight · 2026
Refining Large Language Models with Self-Generated Data Through Iterative Training: Xiao Hu, Muxi Diao, Jizhi Zhang, Xin Chen, Xianyuan Zhan · ICLR 2026 Workshop RSI Poster · 2026
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning: Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel, Angelika Steger, Maciej Wolczyk, Johannes von Oswald, Nino Scherrer, Kaitlin Maile, Guillaume Lajoie, Blake Aaron Richards, Rif A. Saurous, James Manyika, Blaise Aguera y Arcas, Alexander Meulemans, Joao Sacramento · ICLR 2026 Workshop RSI…
Generative Recursive Reasoning Models: Junyeob Baek, Mingyu Jo, Minsu Kim, Yoshua Bengio, Sungjin Ahn · ICLR 2026 Workshop RSI Poster · 2026
Self-Evolving Language Models through Co-evolved Discriminative Rubrics: Shuyue Stella Li, Rui Xin, Yike Wang, Teng Xiao, Rulin Shao, Zoey Hao, Melanie Sclar, Faeze Brahman, Pang Wei Koh, Yulia Tsvetkov · ICLR 2026 Workshop RSI Spotlight · 2026
TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering: Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla · ICLR 2026 Workshop RSI ShortPaper · 2026
Test-Time Self-Distillation: Jonas Hübotter, Frederike Lübeck, Lejs Deen Behric, Anton Baumann, Marco Bagatella, Daniel Marta, Ido Hakimi, Idan Shenfeld, Thomas Kleine Buening, Carlos Guestrin, Andreas Krause · ICLR 2026 Workshop RSI Spotlight · 2026
CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning: Weikun Zhang, Rohan Pandey, Bhaumik Mehta, Kaijie Jin, Naomi Morato, Archit Ganapule, Michael Ruofan Zeng, Jarod Alper · ICLR 2026 Workshop RSI Poster · 2026
Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison: Yoonho Lee, Joseph Boen, Chelsea Finn · ICLR 2026 Workshop RSI Poster · 2026
MimicAgent: Learning Quadruped Skills via Text-to-Trajectory Generation: Narayanan Palghat Parameswaran, Lucky Kant Nayak, Neehar Peri, Deva Ramanan · ICLR 2026 Workshop RSI Poster · 2026
Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences: Sweta Karlekar, Carolina Zheng, Nicolas Beltran-Velez, Magnus Saebo, Shuyang Yu, Michal Kucer, John Bowlan, David Blei · ICLR 2026 Workshop RSI Poster · 2026
Self-Improving VLM Judges Without Human Annotations: Inna Wanyin Lin, Yushi Hu, Shuyue Stella Li, Scott Geng, Pang Wei Koh, Luke Zettlemoyer, Tim Althoff, Marjan Ghazvininejad · ICLR 2026 Workshop RSI Poster · 2026
Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation: Peter Baile Chen, Yi Zhang, Dan Roth, Samuel Madden, Jacob Andreas, Mike Cafarella · ICLR 2026 Workshop RSI Poster · 2026
VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model: Yanjiang Guo, Tony Lee, Lucy Xiaoyang Shi, Jianyu Chen, Percy Liang, Chelsea Finn · ICLR 2026 Workshop RSI Spotlight · 2026
Self-Improving Vision-Language-Action Models with Data Generation via Residual RL: Wenli Xiao, Haotian Lin, Andy Peng, Haoru Xue, Tairan He, Zhengyi Luo, Yuqi Xie, Fengyuan Hu, Linxi Fan, Guanya Shi, Yuke Zhu · ICLR 2026 Workshop RSI Spotlight · 2026
Federation over Text: Dixi Yao, Tahseen Rabbani, Tian Li · ICLR 2026 Workshop RSI ShortPaper · 2026
Soft Mellowmax Monte Carlo Planning: Danilo Vucetic, Gauthier Gidel · ICLR 2026 Workshop RSI Poster · 2026
SAGE: Self-play Adversarial Games Enhance Large Language Model Reasoning Capabilities: Saraswathy Amjith, Michael X. Wang, Jayson Lynch, Hans Gundlach, Neil Thompson · ICLR 2026 Workshop RSI Poster · 2026
Test-Time Meta-Adaptation with Self-Synthesis: Zeyneb N. Kaya, Nick Rui · ICLR 2026 Workshop RSI ShortPaper · 2026
Residual Off-Policy RL for Finetuning Behavior Cloning Policies: Lars Ankile, Zhenyu Jiang, Rocky Duan, Guanya Shi, Pieter Abbeel, Anusha Nagabandi · ICLR 2026 Workshop RSI Poster · 2026
MAPPA: Scaling Multiagent Systems with Process Rewards: Ed Li, Junyu Ren, Cat Yan · ICLR 2026 Workshop RSI Poster · 2026
Depth vs Recursion: Outperforming Transformers in Jigsaw Reconstruction: Artemii Miasoedov, Timofey Brayko, Rustam A. Lukmanov · ICLR 2026 Workshop RSI ShortPaper · 2026
Vision-Guided Iterative Refinement for Frontend Code Generation: Hannah Sansford, Derek H.C. Law, Wei Liu, Abhishek Tripathi, Niresh Agarwal, Gerrit J.J. Van den Burg · ICLR 2026 Workshop RSI Poster · 2026
CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad: Yongqiang Chen, Chenxi Liu, Zhenhao Chen, Tongliang Liu, Bo Han, Kun Zhang · ICLR 2026 Workshop RSI Spotlight · 2026
Dynamic Noise Preference Optimization: Self-Improvement of Large Language Models with Self-Synthetic Data: Haoyan Yang, Le Huy Khiem, Ting Hua, Shangqian Gao, Binfeng Xu, Zheng Tang, Jie Xu, Nitesh V. Chawla, Hongxia Jin, Vijay Srinivasan · ICLR 2026 Workshop RSI Poster · 2026
Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation: Asmita Bhardwaj, Yuya Jeremy Ong, Eelaaf Zahid, Basel Shbita · ICLR 2026 Workshop RSI Poster · 2026
Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models: Shubhangi Upasani, Guangtao Wang, Ravi Shanker Raju, Bo Li, Urmish Thakker, Mengmeng Ji, John Long, Chen Wu · ICLR 2026 Workshop RSI ShortPaper · 2026
A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula: Chenruo Liu, Yijun Dong, Yiqiu Shen, Qi Lei · ICLR 2026 Workshop RSI Poster · 2026
PostTrainBench: Can LLM Agents Automate LLM Post-Training?: Ben Rank, Hardik Bhatnagar, Ameya Prabhu, Shira Eisenberg, Karina Nguyen, Matthias Bethge, Maksym Andriushchenko · ICLR 2026 Workshop RSI Oral · 2026
Can Current Language Models Close the Discovery to Application Loop?: Zhou Ziheng, Huacong Tang, Jinyuan Zhang, Haowei Lin, Bangcheng Yang, Qian Long, Fang Sun, Yizhou Sun, Yitao Liang, Ying Nian Wu, Demetri Terzopoulos, Xiaofeng Gao · ICLR 2026 Workshop RSI Spotlight · 2026
Language-Guided Expertise Evolution for Protein Optimization: Xingyue Liu, Zijie Xing, Runze Wang, Luoming Hu, Yanming Shen · ICLR 2026 Workshop RSI Poster · 2026
Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction: Chengzhi Xu, Yuyang Wang, Lai Wei, Weiran Huang, Lichao Sun · ICLR 2026 Workshop RSI Poster · 2026
Learning to Evolve: Scaling Open-Ended Discovery with Relative-Progress RL: Xuan Li, Zhanke Zhou, Zongze Li, Jiangchao Yao, Bo Han · ICLR 2026 Workshop RSI Poster · 2026
Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback: Sein Kim, Sangwu Park, HongSeok Kang, Wonjoong Kim, Jimin Seo, Yeonjun In, Kanghoon Yoon, Chanyoung Park · ICLR 2026 Workshop RSI Poster · 2026
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models: Qizheng Zhang, Changran Hu, Shubhangi Upasani, Boyuan Ma, Fenglu Hong, Vamsidhar Kamanuru, Jay Rainton, Chen Wu, Mengmeng Ji, Hanchen Li, Urmish Thakker, James Zou, Kunle Olukotun · ICLR 2026 Workshop RSI Poster · 2026
ACE: Self-Evolving LLM Coding Framework Adversarial Unit Test Generation and Preference Optimization: Yixu Huang, Xinglei Yu, zhongyu wei · ICLR 2026 Workshop RSI Spotlight · 2026
Discover the distinguishing and effective reasoning patterns among LLMs via an LLM: Yida Chen, Yuning Mao, Xianjun Yang, Suyu Ge, Shengjie Bi, Lijuan Liu, Saghar Hosseini, Liang Tan, Yixin Nie, Shaoliang Nie · ICLR 2026 Workshop RSI Poster · 2026

Éditions

Liens

Site web: https://iclr.cc
Organisateur: https://iclr.cc