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
AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?
A Theoretical Framework For Overfitting In Energy-based Modeling
A Theoretical Justification for Asymmetric Actor-Critic Algorithms
A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
A Theory for Conditional Generative Modeling on Multiple Data Sources
AtlasD: Automatic Local Symmetry Discovery
A Trichotomy for List Transductive Online Learning
Attention-Level Speculation
Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
Attention-Only Transformers via Unrolled Subspace Denoising
Attributes Shape the Embedding Space of Face Recognition Models
A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
Auditing $f$-differential privacy in one run
Auditing Prompt Caching in Language Model APIs
A Unified Approach to Routing and Cascading for LLMs
A Unified Comparative Study with Generalized Conformity Scores for Multi-Output Conformal Regression
A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization
A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features
A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
AuPair: Golden Example Pairs for Code Repair
AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
AutoAL: Automated Active Learning with Differentiable Query Strategy Search
AutoCATE: End-to-End, Automated Treatment Effect Estimation
AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation
AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling
Autoencoder-Based Hybrid Replay for Class-Incremental Learning
AutoEval Done Right: Using Synthetic Data for Model Evaluation
Autoformulation of Mathematical Optimization Models Using LLMs
AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization
Automated Benchmark Generation for Repository-Level Coding Tasks
Automated Hypothesis Validation with Agentic Sequential Falsifications
Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios
Automatically Interpreting Millions of Features in Large Language Models
Automatic Differentiation of Optimization Algorithms with Time-Varying Updates
Automatic Reward Shaping from Confounded Offline Data
AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
Autonomy-of-Experts Models
Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving
AutoStep: Locally adaptive involutive MCMC
A Variational Framework for Improving Naturalness in Generative Spoken Language Models
A Variational Information Theoretic Approach to Out-of-Distribution Detection
A Variational Perspective on Generative Protein Fitness Optimization
Average Certified Radius is a Poor Metric for Randomized Smoothing
Average Sensitivity of Hierarchical $k$-Median Clustering
A Versatile Influence Function for Data Attribution with Non-Decomposable Loss

« prev Page 6/68 next »