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
Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics
Categorical Schrödinger Bridge Matching
CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration
CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
Causal Abstraction Inference under Lossy Representations
Causal Abstraction Learning based on the Semantic Embedding Principle
Causal Attribution Analysis for Continuous Outcomes
Causal Discovery from Conditionally Stationary Time Series
Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants
Causal Invariance-aware Augmentation for Brain Graph Contrastive Learning
Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection
Causality Inspired Federated Learning for OOD Generalization
Causal Logistic Bandits with Counterfactual Fairness Constraints
Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
CellFlux: Simulating Cellular Morphology Changes via Flow Matching
Censor Dependent Variational Inference
CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning
Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
Certification for Differentially Private Prediction in Gradient-Based Training
Certified Unlearning for Neural Networks
CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models
CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling
Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning
Channel Normalization for Time Series Channel Identification
Chaos Meets Attention: Transformers for Large-Scale Dynamical Prediction
CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
Chip Placement with Diffusion Models
Circumventing Backdoor Space via Weight Symmetry
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models
Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies
Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
Clone-Robust AI Alignment
Closed-form Solutions: A New Perspective on Solving Differential Equations
Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling
CLOVER: Cross-Layer Orthogonal Vectors Pruning
Clustering Items through Bandit Feedback: Finding the Right Feature out of Many
Clustering Properties of Self-Supervised Learning
Clustering via Self-Supervised Diffusion
CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
CoastalBench: A Decade-Long High-Resolution Dataset to Emulate Complex Coastal Processes
CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization
Code-Generated Graph Representations Using Multiple LLM Agents for Material Properties Prediction
CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction
CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance
CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale

« prev Page 10/68 next »