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
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
Toward a Unified Theory of Gradient Descent under Generalized Smoothness
Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
Toward Efficient Kernel-Based Solvers for Nonlinear PDEs
Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
Towards a Formal Theory of Representational Compositionality
Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer
Towards a Mechanistic Explanation of Diffusion Model Generalization
Towards an Explainable Comparison and Alignment of Feature Embeddings
Towards Attributions of Input Variables in a Coalition
Towards a Unified Framework of Clustering-based Anomaly Detection
Towards Better-than-2 Approximation for Constrained Correlation Clustering
Towards Black-Box Membership Inference Attack for Diffusion Models
Towards characterizing the value of edge embeddings in Graph Neural Networks
Towards Cost-Effective Reward Guided Text Generation
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
Towards Escaping from Class Dependency Modeling for Multi-Dimensional Classification
Towards flexible perception with visual memory
Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models
Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
Towards Learning to Complete Anything in Lidar
Towards Lifelong Model Editing via Simulating Ideal Editor
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
Towards Memorization Estimation: Fast, Formal and Free
Towards Practical Defect-Focused Automated Code Review
Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
Towards Real-Time Detection of Squamous PreCancers from Oesophageal Endoscopic Videos
Towards Robust Influence Functions with Flat Validation Minima
Towards Robustness and Explainability of Automatic Algorithm Selection
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
Towards the Causal Complete Cause of Multi-Modal Representation Learning
Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate Shift
Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback
Towards Trustworthy Federated Learning with Untrusted Participants
Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
Towards Understanding Parametric Generalized Category Discovery on Graphs
Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation
TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian Prediction
Tracking Most Significant Shifts in Infinite-Armed Bandits
Tracking The Best Expert Privately
Tractable Transformers for Flexible Conditional Generation
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
Training a Generally Curious Agent
Training Deep Learning Models with Norm-Constrained LMOs
Training Diffusion-based Generative Models with Limited Data
Training Dynamics of In-Context Learning in Linear Attention

« prev Page 63/68 next »