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
Procurement Auctions via Approximately Optimal Submodular Optimization
ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation
Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective
Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
Progressively Label Enhancement for Large Language Model Alignment
Progressive Tempering Sampler with Diffusion
Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
Projection Pursuit Density Ratio Estimation
Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models
Prompt-based Depth Pruning of Large Language Models
Prompt-to-Leaderboard: Prompt-Adaptive LLM Evaluations
ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis
Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features
Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble
Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
ProSec: Fortifying Code LLMs with Proactive Security Alignment
Protein Structure Tokenization: Benchmarking and New Recipe
PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
Proto Successor Measure: Representing the Behavior Space of an RL Agent
Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction
Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
Provable In-Context Vector Arithmetic via Retrieving Task Concepts
Provable Length Generalization in Sequence Prediction via Spectral Filtering
Provable Maximum Entropy Manifold Exploration via Diffusion Models
Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity
Provable Zero-Shot Generalization in Offline Reinforcement Learning
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition
Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
Provably Improving Generalization of Few-shot models with Synthetic Data
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead
PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction
Pruning for GNNs: Lower Complexity with Comparable Expressiveness
PTTA: Purifying Malicious Samples for Test-Time Model Adaptation
Putnam-AXIOM: A Functional & Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation models
QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning Baseline
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
QMamba: On First Exploration of Vision Mamba for Image Quality Assessment
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
QPRL : Learning Optimal Policies with Quasi-Potential Functions for Asymmetric Traversal
Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement Learning
QT-DoG: Quantization-Aware Training for Domain Generalization

« prev Page 49/68 next »