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
Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra
Training High Performance Spiking Neural Network by Temporal Model Calibration
Training Software Engineering Agents and Verifiers with SWE-Gym
Trajectory Inference with Smooth Schrödinger Bridges
Trajectory World Models for Heterogeneous Environments
Transfer Learning for Nonparametric Contextual Dynamic Pricing
Transfer Q-Learning with Composite MDP Structures
Transformative or Conservative? Conservation laws for ResNets and Transformers
Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation
Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometries
TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
Tree-Sliced Wasserstein Distance: A Geometric Perspective
Tree-Sliced Wasserstein Distance with Nonlinear Projection
Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints
Trusted Multi-View Classification with Expert Knowledge Constraints
Trust-Region Twisted Policy Improvement
TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
Trustworthy Machine Learning through Data-Specific Indistinguishability
TruthFlow: Truthful LLM Generation via Representation Flow Correction
TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization
TS-SNN: Temporal Shift Module for Spiking Neural Networks
TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack
TTFSFormer: A TTFS-based Lossless Conversion of Spiking Transformer
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
Tuning LLM Judge Design Decisions for 1/1000 of the Cost
Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization
Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations
TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion
Ultra-Resolution Adaptation with Ease
UltraTWD: Optimizing Ultrametric Trees for Tree-Wasserstein Distance
Unbiased Evaluation of Large Language Models from a Causal Perspective
Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory
Uncertainty Quantification for LLM-Based Survey Simulations
Unconstrained Robust Online Convex Optimization
Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
Understanding and Improving Length Generalization in Recurrent Models
Understanding and Mitigating Memorization in Diffusion Models for Tabular Data
Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
Understanding Bias Reinforcement in LLM Agents Debate
Understanding Chain-of-Thought in LLMs through Information Theory

« prev Page 64/68 next »