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
Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning
Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic Segmentation
Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts
Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning
Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance
Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
Beyond Message Passing: Neural Graph Pattern Machine
Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
Beyond One-Hot Labels: Semantic Mixing for Model Calibration
Beyond Self-Interest: How Group Strategies Reshape Content Creation in Recommendation Platforms?
Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs
Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions
Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion
Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC
Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective
Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly
Bifurcate then Alienate: Incomplete Multi-view Clustering via Coupled Distribution Learning with Linear Overhead
BILBO: BILevel Bayesian Optimization
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
BiMark: Unbiased Multilayer Watermarking for Large Language Models
Binary Hypothesis Testing for Softmax Models and Leverage Score Models
BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security
Bivariate Causal Discovery with Proxy Variables: Integral Solving and Beyond
Black-Box Adversarial Attacks on LLM-Based Code Completion
Blink of an eye: a simple theory for feature localization in generative models
BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
BoA: Attention-aware Post-training Quantization without Backpropagation
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
BOOD: Boundary-based Out-Of-Distribution Data Generation
Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation
Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training
Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners
Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples
Boosting Protein Graph Representations through Static-Dynamic Fusion
Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark
Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema Matching
BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
BounDr.E: Predicting Drug-likeness via Biomedical Knowledge Alignment and EM-like One-Class Boundary Optimization
BoxLM: Unifying Structures and Semantics of Medical Concepts for Diagnosis Prediction in Healthcare
Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO*
Breaking Barriers: Combinatorial Algorithms for Non-Monotone Submodular Maximization with Sublinear Adaptivity and $1/e$ Approximation
Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

« prev Page 8/68 next »