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
MARGE: Improving Math Reasoning with Guided Exploration
MARS: Unleashing the Power of Variance Reduction for Training Large Models
MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
Masked Autoencoders Are Effective Tokenizers for Diffusion Models
Masked Generative Nested Transformers with Decode Time Scaling
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
Mastering Board Games by External and Internal Planning with Language Models
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
Mastering Multiple-Expert Routing: Realizable H-Consistency and Strong Guarantees for Learning to Defer
MathConstruct: Challenging LLM Reasoning with Constructive Proofs
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
Matryoshka Quantization
MATS: An Audio Language Model under Text-only Supervision
Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators
Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization
Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures
Maximum Entropy Reinforcement Learning with Diffusion Policy
Maximum Total Correlation Reinforcement Learning
MCU: An Evaluation Framework for Open-Ended Game Agents
MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models
Measuring Diversity: Axioms and Challenges
Measuring Diversity in Synthetic Datasets
Measuring In-Context Computation Complexity via Hidden State Prediction
Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
Measuring Variable Importance in Heterogeneous Treatment Effects with Confidence
Mechanisms of Projective Composition of Diffusion Models
Mechanistic PDE Networks for Discovery of Governing Equations
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
MedRAX: Medical Reasoning Agent for Chest X-ray
MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge
Memorization Sinks: Isolating Memorization during LLM Training
Memory Layers at Scale
MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs
MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUs
Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
Meta-Black-Box-Optimization through Offline Q-function Learning
Metadata Conditioning Accelerates Language Model Pre-training
Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding

« prev Page 37/68 next »