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
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
Stray Intrusive Outliers-Based Feature Selection on Intra-Class Asymmetric Instance Distribution or Multiple High-Density Clusters
Stream-level Flow Matching with Gaussian Processes
Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM
Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation
Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models
Stronger Neyman Regret Guarantees for Adaptive Experimental Design
Structured Preconditioners in Adaptive Optimization: A Unified Analysis
Structure-Guided Large Language Models for Text-to-SQL Generation
Structure-informed Risk Minimization for Robust Ensemble Learning
Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs
Subgoal-Guided Policy Heuristic Search with Learned Subgoals
Subgroups Matter for Robust Bias Mitigation
Subobject-level Image Tokenization
Sub-Sequential Physics-Informed Learning with State Space Model
Subspace Optimization for Large Language Models with Convergence Guarantees
SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings
Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups
Sundial: A Family of Highly Capable Time Series Foundation Models
Supercharging Graph Transformers with Advective Diffusion
Super Deep Contrastive Information Bottleneck for Multi-modal Clustering
Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching
Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models
Survival Analysis via Density Estimation
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
Symmetry-Aware GFlowNets
Symmetry-Driven Discovery of Dynamical Variables in Molecular Simulations
Symmetry-Robust 3D Orientation Estimation
SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation
Synonymous Variational Inference for Perceptual Image Compression
Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMs
Synthesizing Software Engineering Data in a Test-Driven Manner
Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion
Synthetic Text Generation for Training Large Language Models via Gradient Matching
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
TabFlex: Scaling Tabular Learning to Millions with Linear Attention
TabFSBench: Tabular Benchmark for Feature Shifts in Open Environments
TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
TabNAT: A Continuous-Discrete Joint Generative Framework for Tabular Data
TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems
TabSDS: a Lightweight, Fully Non-Parametric, and Model Free Approach for Generating Synthetic Tabular Data
Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
Taming Diffusion for Dataset Distillation with High Representativeness

« prev Page 59/68 next »