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
Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
Self-Organizing Visual Prototypes for Non-Parametric Representation Learning
Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma
Self-supervised Adversarial Purification for Graph Neural Networks
Self-Supervised Learning of Intertwined Content and Positional Features for Object Detection
Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum
Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction
Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic Images
SEMU: Singular Value Decomposition for Efficient Machine Unlearning
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
Separating Knowledge and Perception with Procedural Data
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
Settling the Maximin Share Fairness for Scheduling among Groups of Machines
Set Valued Predictions For Robust Domain Generalization
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
SHARP-Distill: A 68$\times$ Faster Recommender System with Hypergraph Neural Networks and Language Models
SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models
Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate
Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
SHE: Streaming-media Hashing Retrieval
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy
Shifting Time: Time-series Forecasting with Khatri-Rao Neural Operators
Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts
Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN
Signed Laplacians for Constrained Graph Clustering
Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation
SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
Simple Path Structural Encoding for Graph Transformers
Simple Policy Optimization
Simple Randomized Rounding for Max-Min Eigenvalue Augmentation
Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
Simplifying DINO via Coding Rate Regularization
Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models
Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
SING: Spatial Context in Large Language Model for Next-Gen Wearables
SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems
SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization
SkipGPT: Each Token is One of a Kind

« prev Page 56/68 next »