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
Wasserstein Flow Matching: Generative Modeling Over Families of Distributions
Wasserstein Policy Optimization
WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting
Weakly Supervised Anomaly Detection via Dual-Tailed Kernel
Weakly-Supervised Contrastive Learning for Imprecise Class Labels
Weak-to-Strong Generalization Even in Random Feature Networks, Provably
Weak-to-Strong Jailbreaking on Large Language Models
WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models
Weight matrices compression based on PDB model in deep neural networks
Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction
What can large language models do for sustainable food?
What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning?
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
What If We Recaption Billions of Web Images with LLaMA-3?
What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
What Makes a Good Feedforward Computational Graph?
What makes an Ensemble (Un) Interpretable?
What Makes In-context Learning Effective for Mathematical Reasoning
When and How Does CLIP Enable Domain and Compositional Generalization?
When Bad Data Leads to Good Models
When can in-context learning generalize out of task distribution?
When Can Proxies Improve the Sample Complexity of Preference Learning?
When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
When Do LLMs Help With Node Classification? A Comprehensive Analysis
When do neural networks learn world models?
When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration
When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network
When Maximum Entropy Misleads Policy Optimization
When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class
When to Forget? Complexity Trade-offs in Machine Unlearning
When to retrain a machine learning model
When, Where and Why to Average Weights?
When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
Where is the Truth? The Risk of Getting Confounded in a Continual World
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
Which Attention Heads Matter for In-Context Learning?
Whitened CLIP as a Likelihood Surrogate of Images and Captions
Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors
"Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift
Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
"Why Is There a Tumor?": Tell Me the Reason, Show Me the Evidence
Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg
WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training

« prev Page 67/68 next »