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
Avoiding Catastrophe in Online Learning by Asking for Help
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
Avoiding spurious sharpness minimization broadens applicability of SAM
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Backdoor Attacks in Token Selection of Attention Mechanism
BackSlash: Rate Constrained Optimized Training of Large Language Models
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
Balanced Learning for Domain Adaptive Semantic Segmentation
Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach
Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data
Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing
Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data
BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
BAnG: Bidirectional Anchored Generation for Conditional RNA Design
Banyan: Improved Representation Learning with Explicit Structure
BARK: A Fully Bayesian Tree Kernel for Black-box Optimization
BARNN: A Bayesian Autoregressive and Recurrent Neural Network
Batch List-Decodable Linear Regression via Higher Moments
BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation
BaxBench: Can LLMs Generate Correct and Secure Backends?
Bayesian Active Learning for Bivariate Causal Discovery
Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models
Bayesian Inference for Correlated Human Experts and Classifiers
Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
Bayesian Weight Enhancement with Steady-State Adaptation for Test-time Adaptation in Dynamic Environments
BCE vs. CE in Deep Feature Learning
BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition
Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders
BECAME: Bayesian Continual Learning with Adaptive Model Merging
Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning
Behavior-agnostic Task Inference for Robust Offline In-context Reinforcement Learning
Behavioral Exploration: Learning to Explore via In-Context Adaptation
Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation
Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
Benchmarking Quantum Reinforcement Learning
Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
Benign Overfitting in Token Selection of Attention Mechanism
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
Best of Both Worlds: Regret Minimization versus Minimax Play
BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
Best Subset Selection: Optimal Pursuit for Feature Selection and Elimination
Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance
Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling
Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment

« prev Page 7/68 next »