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
EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification
EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization
Earley-Driven Dynamic Pruning for Efficient Structured Decoding
EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph
EasyInv: Toward Fast and Better DDIM Inversion
EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery
Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges
Editable Concept Bottleneck Models
Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
EditLord: Learning Code Transformation Rules for Code Editing
EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance Prediction
EEG-Language Pretraining for Highly Label-Efficient Clinical Phenotyping
EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation
Effective and Efficient Masked Image Generation Models
Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity
Efficient and Separate Authentication Image Steganography Network
Efficient ANN-SNN Conversion with Error Compensation Learning
Efficient Bisection Projection to Ensure Neural-Network Solution Feasibility for Optimization over General Set
Efficient Core-set Selection for Deep Learning Through Squared Loss Minimization
Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization
Efficient Diffusion Models for Symmetric Manifolds
Efficient Distributed Optimization under Heavy-Tailed Noise
Efficient Federated Incomplete Multi-View Clustering
Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
Efficient Graph Continual Learning via Lightweight Graph Neural Tangent Kernels-based Dataset Distillation
Efficient Heterogeneity-Aware Federated Active Data Selection
Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
Efficient LiDAR Reflectance Compression via Scanning Serialization
Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment
Efficient Long Context Fine-tuning with Chunk Flow
Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
Efficiently Serving Large Multimodal Models Using EPD Disaggregation
Efficiently Vectorized MCMC on Modern Accelerators
Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
Efficient Motion Prompt Learning for Robust Visual Tracking
Efficient Multi-modal Long Context Learning for Training-free Adaptation
Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
Efficient Network Automatic Relevance Determination
Efficient Noise Calculation in Deep Learning-based MRI Reconstructions
Efficient Online Reinforcement Learning for Diffusion Policy
Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method
Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
Efficient Personalized Adaptation for Physiological Signal Foundation Model
Efficient Quantification of Multimodal Interaction at Sample Level
Efficient Robotic Policy Learning via Latent Space Backward Planning
Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks

« prev Page 18/68 next »