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
NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones
No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
Noise Conditional Variational Score Distillation
Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation
Noisy SIGNSGD Is More Differentially Private Than You (Might) Think
NoLiMa: Long-Context Evaluation Beyond Literal Matching
No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets
Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails
Non-asymptotic Error Bounds in $\mathcal{W}_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity
Non-asymptotic Error Bounds in W2-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity
Non-Asymptotic Length Generalization
Nonconvex Theory of $M$-estimators with Decomposable Regularizers
Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
Nonlinear transformers can perform inference-time feature learning
Nonparametric Identification of Latent Concepts
Nonparametric Modern Hopfield Models
Nonparametric Teaching for Graph Property Learners
Non-stationary Diffusion For Probabilistic Time Series Forecasting
Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics
No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization
Normalizing Flows are Capable Generative Models
No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks
Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers
Not All Wrong is Bad: Using Adversarial Examples for Unlearning
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
Novelty Detection in Reinforcement Learning with World Models
NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel
NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
Objective drives the consistency of representational similarity across datasets
Observation Interference in Partially Observable Assistance Games
Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference
Offline Learning for Combinatorial Multi-armed Bandits
Offline Model-based Optimization for Real-World Molecular Discovery
Offline Opponent Modeling with Truncated Q-driven Instant Policy Refinement
Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation
Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
Off-Policy Evaluation under Nonignorable Missing Data
Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents
Olica: Efficient Structured Pruning of Large Language Models without Retraining
O-MAPL: Offline Multi-agent Preference Learning
OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation
Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
OmniArch: Building Foundation Model for Scientific Computing
OmniAudio: Generating Spatial Audio from 360-Degree Video
OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance
On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
On Differential Privacy for Adaptively Solving Search Problems via Sketching
One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model Trajectory

« prev Page 41/68 next »