ICLR 2026
5,370 papers
Top Research Directions
Research directions most represented by ICLR 2026 papers.
Top Authors
| Author | Papers |
|---|---|
| Fei Huang | 20 |
| Ge Zhang | 19 |
| Jianye HAO | 19 |
| Dahua Lin | 17 |
| Junchi Yan | 17 |
| Michael M. Bronstein | 17 |
| Yejin Choi | 17 |
| James Y. Zou | 16 |
| James Zou | 16 |
| Bo Han | 15 |
| Jingren Zhou | 15 |
| Min Zhang | 15 |
| Tat-Seng Chua | 15 |
| Caiming Xiong | 14 |
| Dawn Song | 14 |
| Pengfei Wan | 14 |
| Yi Yang | 14 |
| Jiaheng Liu | 13 |
| Kai Chen | 13 |
| Pengjun Xie | 13 |
Impactful Papers
Papers from ICLR 2026 that shaped research clusters.
Foundational
Learning Correlated Reward Models: Statistical Barriers and Opportunities
foundational
The Statistical Limits of Pairwise Prefe
Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Leng
foundational
Preventing Reasoning Collapse in Constra
A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
foundational
Why Safety Alignment Fails Beyond the In
REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning
foundational
Preventing Reasoning Collapse in Constra
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
foundational
Why Safety Alignment Fails Beyond the In
Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Re
foundational
Reward Variance Filtering for Policy Opt
Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy Optimizat
foundational
Reward Variance Filtering for Policy Opt
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
foundational
Mitigating Overthinking in Large Reasoni
Learning to Reason Efficiently with Discounted Reinforcement Learning
foundational
Preventing Reasoning Collapse in Constra
DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
foundational
Preventing Reasoning Collapse in Constra