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
Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms
Learning Mixtures of Experts with EM: A Mirror Descent Perspective
Learning Monotonic Probabilities with a Generative Cost Model
Learning Multi-Level Features with Matryoshka Sparse Autoencoders
Learning multivariate Gaussians with imperfect advice
Learning Optimal Multimodal Information Bottleneck Representations
Learning-Order Autoregressive Models with Application to Molecular Graph Generation
Learning Parametric Distributions from Samples and Preferences
Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks
Learning Progress Driven Multi-Agent Curriculum
Learning Representations of Instruments for Partial Identification of Treatment Effects
Learning Robust 3D Representation from CLIP via Dual Denoising
Learning Robust Neural Processes with Risk-Averse Stochastic Optimization
Learning Safe Control via On-the-Fly Bandit Exploration
Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions
Learning Safety Constraints for Large Language Models
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation
Learning Single Index Models with Diffusion Priors
Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction
Learning Soft Sparse Shapes for Efficient Time-Series Classification
Learning State-Based Node Representations from a Class Hierarchy for Fine-Grained Open-Set Detection
Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
Learning Survival Distributions with the Asymmetric Laplace Distribution
Learning the Electronic Hamiltonian of Large Atomic Structures
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains
Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes
Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems
Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Learning to Match Unpaired Data with Minimum Entropy Coupling
Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
Learning to Quantize for Training Vector-Quantized Networks
Learning to Reuse Policies in State Evolvable Environments
Learning to Route LLMs with Confidence Tokens
Learning to Steer Learners in Games
Learning to Stop: Deep Learning for Mean Field Optimal Stopping
Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
Learning Utilities from Demonstrations in Markov Decision Processes
Learning Vision and Language Concepts for Controllable Image Generation
Learning with Exact Invariances in Polynomial Time
Learning with Expected Signatures: Theory and Applications
Learning With Multi-Group Guarantees For Clusterable Subpopulations
Learning without Isolation: Pathway Protection for Continual Learning
Learning with Selectively Labeled Data from Multiple Decision-makers
Learn Singularly Perturbed Solutions via Homotopy Dynamics
Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak Control
Learnware Specification via Dual Alignment
Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams

« prev Page 34/68 next »