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
CoDy: Counterfactual Explainers for Dynamic Graphs
COExpander: Adaptive Solution Expansion for Combinatorial Optimization
CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning
CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention
COKE: Core Kernel for More Efficient Approximation of Kernel Weights in Multiple Kernel Clustering
CollabLLM: From Passive Responders to Active Collaborators
Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution
Collapse or Thrive: Perils and Promises of Synthetic Data in a Self-Generating World
Collapse-Proof Non-Contrastive Self-Supervised Learning
CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generation
Combinatorial Reinforcement Learning with Preference Feedback
CoMemo: LVLMs Need Image Context with Image Memory
Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation
Communicating Activations Between Language Model Agents
Commute Graph Neural Networks
CommVQ: Commutative Vector Quantization for KV Cache Compression
Compact Matrix Quantum Group Equivariant Neural Networks
Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability Queries
Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method
Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training
Competing Bandits in Matching Markets via Super Stability
Competitively Consistent Clustering
Complete-Tree Space Favors Data-Efficient Link Prediction
Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation
Componential Prompt-Knowledge Alignment for Domain Incremental Learning
Compositional Causal Reasoning Evaluation in Language Models
Compositional Condition Question Answering in Tabular Understanding
Compositional Flows for 3D Molecule and Synthesis Pathway Co-design
Compositional Generalization via Forced Rendering of Disentangled Latents
Compositional Risk Minimization
Compositional Scene Understanding through Inverse Generative Modeling
Compressed Image Generation with Denoising Diffusion Codebook Models
Compressing tree ensembles through Level-wise Optimization and Pruning
Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
Compute or Load KV Cache? Why Not Both?
Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows
Computing Voting Rules with Improvement Feedback
COMRECGC: Global Graph Counterfactual Explainer through Common Recourse
Concentration Distribution Learning from Label Distributions
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Concept-Based Unsupervised Domain Adaptation
Concept-Centric Token Interpretation for Vector-Quantized Generative Models
Concept Reachability in Diffusion Models: Beyond Dataset Constraints
Concurrent Reinforcement Learning with Aggregated States via Randomized Least Squares Value Iteration
Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting
Conditioning Diffusions Using Malliavin Calculus
Confidence Difference Reflects Various Supervised Signals in Confidence-Difference Classification

« prev Page 11/68 next »