ICLR

20,232 papers11,258 directions

Papers by Year

2026 5,370
2025 3,823
2024 2,461
2023 3,358
2022 2,337
2021 937
2020 718
2019 514
2018 387
2017 258
2016 147
2015 166
2014 97
2013 80
2012 2
2011 1

Top Research Directions

Research directions most represented by papers from this venue.

Shifting from Static Benchmarks to Dynamic Evaluation 155
Clean Accuracy Degradation in Machine Learning Defenses 143
Bypassing the Computational Bottleneck of Adversarial Training 141
Sample Efficient Reinforcement Learning 112
General Purpose Reasoning from Specialized Reinforcement Learning 111
Overcoming the Iterative Inference Latency of Diffusion Models 103
Scaling Language Model Reasoning Beyond Verifiable Rewards 95
The Mechanics of Benign Overfitting in High Dimensions 92
Group Relative Policy Optimization for Large Reasoning Models 83
Mitigating Gradient Variance in Policy Optimization 81
The Performance Cliff in Ultra Low Bit Quantization 80
Accelerating Sparse Neural Networks on Dense Hardware 79
Over-Smoothing in Graph Neural Networks 77
Navigating Non-Convex Loss Landscapes in Deep Learning 76
The Decoupling of Visual Perception and Logical Reasoning 74

Top Authors

AuthorPapers
Sergey Levine131
Yoshua Bengio125
Junchi Yan81
Zhangyang Wang77
Bo Han71
Tongliang Liu68
Pieter Abbeel65
Joshua B. Tenenbaum64
Chelsea Finn62
Aaron Courville59
Caiming Xiong59
Dacheng Tao59
Jun Zhu57
Bernhard Schölkopf56
Jianye HAO55
Kun Zhang53
Stefano Ermon53
Mihaela van der Schaar50
Sung Ju Hwang50
J Zico Kolter48

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels2026
WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection2026
WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization2026
WebWatcher: Breaking New Frontiers of Vision-Language Deep Research Agent2026
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research2026
W-EDIT: A Wavelet-Based Frequency-Aware Framework for Text-Driven Image Editing2026
Weight Decay may matter more than µP for Learning Rate Transfer in Practice2026
Weight-Space Linear Recurrent Neural Networks2026
Weight Space Representation Learning on Diverse NeRF Architectures2026
Welfarist Formulations for Diverse Similarity Search2026
We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning2026
WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction2026
WFR-FM: Simulation-Free Dynamic Unbalanced Optimal Transport2026
What Do Large Language Models Know About Opinions?2026
Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity2026
What Exactly Does Guidance Do in Masked Discrete Diffusion Models2026
What Generative Search Engines Like and How to Optimize Web Content Cooperatively2026
What Happens Next? Anticipating Future Motion by Generating Point Trajectories2026
What happens when generative AI models train recursively on each others' outputs?2026
What Layers When: Learning to Skip Compute in LLMs with Residual Gates2026
What Matters for Batch Online Reinforcement Learning in Robotics?2026
What matters for Representation Alignment: Global Information or Spatial Structure?2026
What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging2026
What Scales in Cross-Entropy Scaling Law?2026
What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data2026
What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering2026
When Agents “Misremember” Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems2026
When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms2026
When and Where to Reset Matters for Long-Term Test-Time Adaptation2026
When a Robot is More Capable than a Human: Learning from Constrained Demonstrators2026
When Bias Meets Trainability: Connecting Theories of Initialization2026
When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets2026
When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework2026
When Flatness Does (Not) Guarantee Adversarial Robustness2026
When Foundation Models are One-Liners: Limitations and Future Directions for Time Series Anomaly Detection2026
When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training2026
When Is Diversity Rewarded in Cooperative Multi-Agent Learning?2026
When Language Models Lose Their Mind: The Consequences of Brain Misalignment2026
When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations2026
When LLMs get significantly worse: A statistical approach to detect model degradations2026
When Machine Learning Gets Personal: Evaluating Prediction and Explanation2026
When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMs2026
When More is Less: Understanding Chain-of-Thought Length in LLMs2026
When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining2026
When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models2026
When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis2026
When Shift Happens - Confounding Is to Blame2026
When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?2026
When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment2026
When Thinking Backfires: Mechanistic Insights into Reason-induced Misalignment2026

« prev Page 106/405 next »