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
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
Conformal Anomaly Detection in Event Sequences
Conformal Prediction as Bayesian Quadrature
Conformal Prediction with Cellwise Outliers: A Detect-then-Impute Approach
Conformal Tail Risk Control for Large Language Model Alignment
Conformity Score Averaging for Classification
Confounder-Free Continual Learning via Recursive Feature Normalization
ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
Consensus Based Stochastic Optimal Control
Consensus Is All You Get: The Role of Attention in Transformers
Conservative Offline Goal-Conditioned Implicit V-Learning
Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
Constrain Alignment with Sparse Autoencoders
Constrained Belief Updates Explain Geometric Structures in Transformer Representations
Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium
Constrained Online Convex Optimization with Polyak Feasibility Steps
Constrained Pareto Set Identification with Bandit Feedback
ConText: Driving In-context Learning for Text Removal and Segmentation
Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré–Hopf Theorem
Context is Key: A Benchmark for Forecasting with Essential Textual Information
Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images
Contextual Bandits for Unbounded Context Distributions
Contextual Linear Bandits with Delay as Payoff
Contextual Online Decision Making with Infinite-Dimensional Functional Regression
Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach
Contextures: Representations from Contexts
Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
Continual Reinforcement Learning by Planning with Online World Models
Continuous Bayesian Model Selection for Multivariate Causal Discovery
Continuously Updating Digital Twins using Large Language Models
Continuous Semi-Implicit Models
Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games
Continuous Visual Autoregressive Generation via Score Maximization
Contour Integration Underlies Human-Like Vision
Contract Design Under Approximate Best Responses
Contradiction Retrieval via Contrastive Learning with Sparsity
Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification
Contrastive Localized Language-Image Pre-Training
Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion
Contrastive Visual Data Augmentation
Control and Realism: Best of Both Worlds in Layout-to-Image without Training
Controllable Data Generation with Hierarchical Neural Representations
Controlled Generation with Equivariant Variational Flow Matching
Controlling Large Language Model with Latent Action
Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning
Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration
Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity
Convergence of Consistency Model with Multistep Sampling under General Data Assumptions
Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization

« prev Page 12/68 next »