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
Resolving Lexical Bias in Model Editing
ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
Rethink GraphODE Generalization within Coupled Dynamical System
Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding
Rethinking Aleatoric and Epistemic Uncertainty
Rethinking Benign Overfitting in Two-Layer Neural Networks
Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation
Rethinking Chain-of-Thought from the Perspective of Self-Training
Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation
Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation
Rethinking Score Distilling Sampling for 3D Editing and Generation
Rethinking the Bias of Foundation Model under Long-tailed Distribution
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
Rethinking the Temperature for Federated Heterogeneous Distillation
Rethinking Time Encoding via Learnable Transformation Functions
Rethink the Role of Deep Learning towards Large-scale Quantum Systems
Retraining-free Merging of Sparse MoE via Hierarchical Clustering
Retraining with Predicted Hard Labels Provably Increases Model Accuracy
Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding
Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG
Retrieval Augmented Time Series Forecasting
Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate
Return Capping: Sample Efficient CVaR Policy Gradient Optimisation
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces
Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks
ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification
Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding?
Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning
Revisiting Differentially Private Algorithms for Decentralized Online Learning
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model
Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective
Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG Analysis
Revisiting Non-Acyclic GFlowNets in Discrete Environments
Revisiting the Predictability of Performative, Social Events
Revisiting Unbiased Implicit Variational Inference
Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization.
Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
Reward-free World Models for Online Imitation Learning
Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design
Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs
Reward-Guided Speculative Decoding for Efficient LLM Reasoning

« prev Page 52/68 next »