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
Models of Heavy-Tailed Mechanistic Universality
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Model Uncertainty Quantification by Conformal Prediction in Continual Learning
Modified K-means Algorithm with Local Optimality Guarantees
Modular Duality in Deep Learning
Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering
Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization
MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning
MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition
MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
MoH: Multi-Head Attention as Mixture-of-Head Attention
Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition
Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
Monte Carlo Tree Diffusion for System 2 Planning
Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport
MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles
More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions
Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models
MP-Nav: Enhancing Data Poisoning Attacks against Multimodal Learning
MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment
MTL-UE: Learning to Learn Nothing for Multi-Task Learning
MTSTRec: Multimodal Time-Aligned Shared Token Recommender
MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost
Multiaccuracy and Multicalibration via Proxy Groups
Multi-agent Architecture Search via Agentic Supernet
Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits
Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding
Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion
Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference
Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points
Multimodal Medical Code Tokenizer
Multi-Modal Object Re-identification via Sparse Mixture-of-Experts
Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints
Multi-Objective Causal Bayesian Optimization
Multiobjective distribution matching
Multi-objective Linear Reinforcement Learning with Lexicographic Rewards
MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
Multiple-policy Evaluation via Density Estimation
Multi-Session Budget Optimization for Forward Auction-based Federated Learning
Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks
Multi-Turn Code Generation Through Single-Step Rewards

« prev Page 39/68 next »