ICML 2025

3,384 papers

Top Research Directions

Research directions most represented by ICML 2025 papers.

Shifting from Static Benchmarks to Dynamic Evaluation 37
Inference Time Compute Scaling for Complex Reasoning 30
Clean Accuracy Degradation in Machine Learning Defenses 29
Overcoming the Iterative Inference Latency of Diffusion Models 27
The Performance Cliff in Ultra Low Bit Quantization 27
The Computational Overhead of Generative Data Synthesis 23
Bypassing the Computational Bottleneck of Adversarial Training 23
Outlier Suppression for Low Bit Transformer Quantization 20
The Function Approximation Gap in Reinforcement Learning Theory 20
Understanding Training Data Memorization in Generative Models 18
Resolving Superposition with Sparse Autoencoders 17
Preserving Model Utility During Machine Unlearning 17
Adapting Graph Neural Networks to Evolving Topologies 17
Overcoming the Homophily Assumption in Graph Neural Networks 16
Over-Smoothing in Graph Neural Networks 16

Top Authors

AuthorPapers
Mihaela van der Schaar15
Dacheng Tao12
Guancheng Wan12
Li Shen12
Mang Ye12
Wenke Huang12
Sergey Levine11
Kun Zhang10
Quanquan Gu10
Sanmi Koyejo10
Bo Han9
Feng Liu9
Ion Stoica9
Junchi Yan9
Martin Vechev9
Ruixuan Li9
Shirui Pan9
Yu Cheng9
Jiang Bian8
Jun Zhu8

Impactful Papers

Papers from ICML 2025 that shaped research clusters.

Foundational

Influential

Papers

Title
The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning
The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
The Case for Learned Provenance-based System Behavior Baseline
The Complexity of Learning Sparse Superposed Features with Feedback
The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning
The dark side of the forces: assessing non-conservative force models for atomistic machine learning
The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
The Diffusion Duality
The Disparate Benefits of Deep Ensembles
The Double-Ellipsoid Geometry of CLIP
The Elicitation Game: Evaluating Capability Elicitation Techniques
The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination
The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
The Four Color Theorem for Cell Instance Segmentation
The Generalized Skew Spectrum of Graphs
The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks
The impact of uncertainty on regularized learning in games
The Importance of Being Lazy: Scaling Limits of Continual Learning
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
The Limits of Predicting Agents from Behaviour
The Limits of Tractable Marginalization
The Lock-in Hypothesis: Stagnation by Algorithm
The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
The Missing Alignment Link of In-context Learning on Sequences
The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction
The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
Theoretical guarantees on the best-of-n alignment policy
Theoretical Limitations of Ensembles in the Age of Overparameterization
Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
The Polynomial Stein Discrepancy for Assessing Moment Convergence
The Power of Random Features and the Limits of Distribution-Free Gradient Descent
The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products
The Price of Linear Time: Error Analysis of Structured Kernel Interpolation
The Relationship Between No-Regret Learning and Online Conformal Prediction
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
The Role of Randomness in Stability

« prev Page 61/68 next »