ICML

23,199 papers12,206 directions

Papers by Year

2026 6,487
2025 3,384
2024 2,660
2023 1,862
2022 1,154
2021 1,200
2020 1,099
2019 797
2018 644
2017 440
2016 331
2015 277
2014 314
2013 287
2012 267
2011 158
2010 161
2009 187
2008 164
2007 155
2006 142
2005 137
2004 118
2003 118
2002 87
2001 80
2000 153
1999 55
1998 67
1997 47
1996 67
1995 72
1994 43
1993 45
1991 1
1990 1
1988 1

Top Research Directions

Research directions most represented by papers from this venue.

Scaling Gaussian Processes Beyond Cubic Complexity 181
The Non-Linear Function Approximation Gap in Reinforcement Learning 173
Clean Accuracy Degradation in Machine Learning Defenses 161
Bypassing the Computational Bottleneck of Adversarial Training 133
Overcoming the Iterative Inference Latency of Diffusion Models 132
The Function Approximation Gap in Reinforcement Learning Theory 120
Mitigating Gradient Variance in Policy Optimization 117
Sample Efficient Reinforcement Learning 111
Safe Reinforcement Learning via Constrained Markov Decision Processes 109
Shifting from Static Benchmarks to Dynamic Evaluation 106
Matrix-Free Curvature Estimation for Deep Learning 105
Mitigating Gradient Variance in Stochastic Optimization 102
Scaling Reinforcement Learning to High-Dimensional Visual Observations 96
The Performance Cliff in Ultra Low Bit Quantization 96
Optimization and Generalization with Non-Smooth Activations 94

Top Authors

AuthorPapers
Bernhard Schölkopf84
Michael Jordan81
Masashi Sugiyama75
Sergey Levine75
Yoshua Bengio73
Jun Zhu72
Quanquan Gu69
Shie Mannor66
Mihaela van der Schaar63
Bo Han57
Andreas Krause56
Eric P. Xing55
Pieter Abbeel55
Stefano Ermon55
Percy Liang54
Zhangyang Wang54
Junchi Yan53
Remi Munos53
Csaba Szepesvari51
Tongliang Liu51

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Policy-Regret Minimization in Markov Games with Function Approximation2025
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning2025
Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications2025
polybasic Speculative Decoding Through a Theoretical Perspective2025
PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models2025
Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules2025
Polynomial-Time Approximability of Constrained Reinforcement Learning2025
Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems2025
POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval2025
POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization2025
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models2025
Position: AI Agents Need Authenticated Delegation2025
Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation2025
Position: AI Evaluation Should Learn from How We Test Humans2025
Position: AI Safety Must Embrace an Antifragile Perspective2025
Position: AI Safety should prioritize the Future of Work2025
Position: AI Scaling: From Up to Down and Out2025
Position: AI's growing due process problem2025
Position: AI Should Not Be An Imitation Game: Centaur Evaluations2025
Positional Attention: Expressivity and Learnability of Algorithmic Computation2025
Positional Encoding meets Persistent Homology on Graphs2025
Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry2025
Position: All Current Generative Fidelity and Diversity Metrics are Flawed2025
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research2025
Position: A Theory of Deep Learning Must Include Compositional Sparsity2025
Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care2025
Position: Build Agent Advocates, Not Platform Agents2025
Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption2025
Position: Certified Robustness Does Not (Yet) Imply Model Security2025
Position: Challenges and Future Directions of Data-Centric AI Alignment2025
Position: Constants are Critical in Regret Bounds for Reinforcement Learning2025
Position: Contextual Integrity is Inadequately Applied to Language Models2025
Position: Current Model Licensing Practices are Dragging Us into a Quagmire of Legal Noncompliance2025
Position: Deep Learning is Not So Mysterious or Different2025
Position: Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work.2025
Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints2025
Position: Editing Large Language Models Poses Serious Safety Risks2025
Position: Enough of Scaling LLMs! Lets Focus on Downscaling2025
Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge2025
Position: Explainable AI Cannot Advance Without Better User Studies2025
Position: Formal Mathematical Reasoning—A New Frontier in AI2025
Position: Future Research and Challenges Remain Towards AI for Software Engineering2025
Position: General Intelligence Requires Reward-based Pretraining2025
Position: Generative AI Regulation Can Learn from Social Media Regulation2025
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks2025
Position: Graph Matching Systems Deserve Better Benchmarks2025
Position: Human Baselines in Model Evaluations Need Rigor and Transparency (With Recommendations & Reporting Checklist)2025
Position: Humanity Faces Existential Risk from Gradual Disempowerment2025
Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI2025
Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks2025

« prev Page 176/464 next »