NeurIPS

31,469 papers14,757 directions

Papers by Year

2026 13
2025 5,812
2024 4,579
2023 3,621
2022 2,923
2021 2,712
2020 1,908
2019 1,442
2018 1,011
2017 718
2016 574
2015 410
2014 416
2013 366
2012 379
2011 311
2010 307
2009 268
2008 256
2007 221
2006 209
2005 212
2004 212
2003 202
2002 211
2001 200
2000 155
1999 152
1998 152
1997 157
1996 153
1995 161
1994 149
1993 166
1992 142
1991 151
1990 172
1989 108
1988 100
1987 90

Top Research Directions

Research directions most represented by papers from this venue.

Scaling Gaussian Processes Beyond Cubic Complexity 263
Bypassing the Computational Bottleneck of Adversarial Training 159
The Non-Linear Function Approximation Gap in Reinforcement Learning 158
Clean Accuracy Degradation in Machine Learning Defenses 155
Safe Reinforcement Learning via Constrained Markov Decision Processes 144
The Mechanics of Benign Overfitting in High Dimensions 144
Multi-Agent Learning Under Bandit Feedback 137
Non-linear Modeling of Neural Population Dynamics 126
Overcoming the Cubic Complexity of Kernel Methods 123
Matrix-Free Curvature Estimation for Deep Learning 120
Kernel Hyperparameter Sensitivity in Distributional Metrics 118
The Statistical Computational Gap in High Dimensions 115
Overcoming the Iterative Inference Latency of Diffusion Models 113
Non-linear Causal Discovery via Functional Constraints 109
Mitigating Gradient Variance in Stochastic Optimization 108

Top Authors

AuthorPapers
Michael Jordan147
Bernhard Schölkopf122
Yoshua Bengio112
Joshua B. Tenenbaum100
Sergey Levine94
Andreas Krause86
Stefano Ermon85
Francis Bach81
Jun Zhu74
Dacheng Tao73
Pieter Abbeel72
Pradeep Kumar Ravikumar72
Mihaela van der Schaar70
Eric P. Xing68
Masashi Sugiyama67
Tong Zhang67
Zhangyang Wang64
Kun Zhang63
Nathan Srebro62
Sham M. Kakade61

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents2025
WebThinker: Empowering Large Reasoning Models with Deep Research Capability2025
WEDGE: Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency2025
We Should Chart an Atlas of All the World's Models2025
WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making2025
WhAM: Towards A Translative Model of Sperm Whale Vocalization2025
What are you sinking? A geometric approach on attention sink2025
What Can RL Bring to VLA Generalization? An Empirical Study2025
What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization2025
What Does It Take to Build a Performant Selective Classifier?2025
What Do Latent Action Models Actually Learn?2025
What do you know? Bayesian knowledge inference for navigating agents2025
What Expressivity Theory Misses: Message Passing Complexity for GNNs2025
What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers2025
What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions2025
What Makes a Reward Model a Good Teacher? An Optimization Perspective2025
WHAT MAKES MATH PROBLEMS HARD FOR REINFORCEMENT LEARNING: A CASE STUDY2025
What Matters in Data for DPO?2025
What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses2025
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains2025
What Really is a Member? Discrediting Membership Inference via Poisoning2025
What’s in Common? Multimodal Models Hallucinate When Reasoning Across Scenes2025
What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models2025
What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers2025
When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery2025
When and how can inexact generative models still sample from the data manifold?2025
When and How Unlabeled Data Provably Improve In-Context Learning2025
When Are Concepts Erased From Diffusion Models?2025
When Can Model-Free Reinforcement Learning be Enough for Thinking?2025
When Causal Dynamics Matter: Adapting Causal Strategies through Meta-Aware Interventions2025
⁠When Data Can't Meet: Estimating Correlation Across Privacy Barriers2025
When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective2025
When Does Curriculum Learning Help? A Theoretical Perspective2025
When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective2025
When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product2025
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners2025
When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses2025
When majority rules, minority loses: bias amplification of gradient descent2025
When Models Don’t Collapse: On the Consistency of Iterative MLE2025
When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration2025
When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning2025
When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions2025
When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding2025
When Thinking Drifts: Evidential Grounding for Robust Video Reasoning2025
When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs2025
When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization2025
Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models2025
Where Does It Exist from the Low-Altitude: Spatial Aerial Video Grounding2025
Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts2025
Which Algorithms Have Tight Generalization Bounds?2025

« prev Page 115/630 next »