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
Improving Out-of-Distribution Detection via Dynamic Covariance Calibration
Improving Out-of-Distribution Detection with Markov Logic Networks
Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces
Improving Rationality in the Reasoning Process of Language Models through Self-playing Game
Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
Improving Soft Unification with Knowledge Graph Embedding Methods
Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning
Improving the Diffusability of Autoencoders
Improving the Effective Receptive Field of Message-Passing Neural Networks
Improving the Scaling Laws of Synthetic Data with Deliberate Practice
Improving the Statistical Efficiency of Cross-Conformal Prediction
Improving the Variance of Differentially Private Randomized Experiments through Clustering
Improving Transformer World Models for Data-Efficient RL
Improving Value Estimation Critically Enhances Vanilla Policy Gradient
Improving Your Model Ranking on Chatbot Arena by Vote Rigging
Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices
IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
iN2V: Bringing Transductive Node Embeddings to Inductive Graphs
Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
In-Context Adaptation to Concept Drift for Learned Database Operations
In-Context Deep Learning via Transformer Models
In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
In-Context Fine-Tuning for Time-Series Foundation Models
In-Context Learning and Occam's Razor
In-Context Learning as Conditioned Associative Memory Retrieval
In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention
In-Context Reinforcement Learning From Suboptimal Historical Data
Incorporating Arbitrary Matrix Group Equivariance into KANs
Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems
Independence Tests for Language Models
Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning
Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations
Inductive Moment Matching
InfAlign: Inference-aware language model alignment
Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models
Info-Coevolution: An Efficient Framework for Data Model Coevolution
InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting
InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference
INRFlow: Flow Matching for INRs in Ambient Space
Instance Correlation Graph-based Naive Bayes
Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
Instruct2See: Learning to Remove Any Obstructions Across Distributions
Instruction-Following Pruning for Large Language Models
Integer Programming for Generalized Causal Bootstrap Designs
Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models
Integration-free Kernels for Equivariant Gaussian Process Modelling
Interaction-Aware Gaussian Weighting for Clustered Federated Learning

« prev Page 30/68 next »