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
On the Generalization Ability of Next-Token-Prediction Pretraining
On the Guidance of Flow Matching
On the Impact of Performative Risk Minimization for Binary Random Variables
On the Importance of Embedding Norms in Self-Supervised Learning
On the Importance of Gaussianizing Representations
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
On the Learnability of Distribution Classes with Adaptive Adversaries
On the Local Complexity of Linear Regions in Deep ReLU Networks
On the Out-of-Distribution Generalization of Self-Supervised Learning
On the Power of Context-Enhanced Learning in LLMs
On the Power of Learning-Augmented Search Trees
On the Private Estimation of Smooth Transport Maps
On the Provable Separation of Scales in Maximal Update Parameterization
On the Query Complexity of Verifier-Assisted Language Generation
On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents
On the Robustness of Reward Models for Language Model Alignment
On the Role of Label Noise in the Feature Learning Process
On the Similarities of Embeddings in Contrastive Learning
On the Statistical Mechanisms of Distributional Compositional Generalization
On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning
On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
On Understanding Attention-Based In-Context Learning for Categorical Data
On Volume Minimization in Conformal Regression
On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation
OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
Open-Det: An Efficient Learning Framework for Open-Ended Detection
Open Materials Generation with Stochastic Interpolants
OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning
Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction
Optimal Algorithm for Max-Min Fair Bandit
Optimal and Practical Batched Linear Bandit Algorithm
Optimal Auction Design in the Joint Advertising
Optimal Decision Tree Pruning Revisited: Algorithms and Complexity
Optimal Fair Learning Robust to Adversarial Distribution Shift
Optimal Information Retention for Time-Series Explanations
Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics
Optimal Survey Design for Private Mean Estimation
Optimal Task Order for Continual Learning of Multiple Tasks
Optimal Transfer Learning for Missing Not-at-Random Matrix Completion
Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization
Optimal transport-based conformal prediction
Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect
Optimization for Neural Operators can Benefit from Width
Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach
Optimizing Adaptive Attacks against Watermarks for Language Models
Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
Optimizing Large Language Model Training Using FP4 Quantization
Optimizing Noise Distributions for Differential Privacy

« prev Page 43/68 next »