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
Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion
PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning
Point Cloud Dataset Distillation
Point-Level Topological Representation Learning on Point Clouds
Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study
PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data
PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models
PokéChamp: an Expert-level Minimax Language Agent
Policy Design for Two-sided Platforms with Participation Dynamics
Policy Filtration for RLHF to Mitigate Noise in Reward Models
Policy Gradient with Tree Expansion
Policy Guided Tree Search for Enhanced LLM Reasoning
Policy-labeled Preference Learning: Is Preference Enough for RLHF?
Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
Policy-Regret Minimization in Markov Games with Function Approximation
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications
polybasic Speculative Decoding Through a Theoretical Perspective
PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models
Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules
Polynomial-Time Approximability of Constrained Reinforcement Learning
Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems
POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
Position: AI Agents Need Authenticated Delegation
Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation
Position: AI Evaluation Should Learn from How We Test Humans
Position: AI Safety Must Embrace an Antifragile Perspective
Position: AI Safety should prioritize the Future of Work
Position: AI Scaling: From Up to Down and Out
Position: AI's growing due process problem
Position: AI Should Not Be An Imitation Game: Centaur Evaluations
Positional Attention: Expressivity and Learnability of Algorithmic Computation
Positional Encoding meets Persistent Homology on Graphs
Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
Position: All Current Generative Fidelity and Diversity Metrics are Flawed
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
Position: A Theory of Deep Learning Must Include Compositional Sparsity
Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care
Position: Build Agent Advocates, Not Platform Agents
Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption
Position: Certified Robustness Does Not (Yet) Imply Model Security
Position: Challenges and Future Directions of Data-Centric AI Alignment
Position: Constants are Critical in Regret Bounds for Reinforcement Learning
Position: Contextual Integrity is Inadequately Applied to Language Models
Position: Current Model Licensing Practices are Dragging Us into a Quagmire of Legal Noncompliance
Position: Deep Learning is Not So Mysterious or Different
Position: Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work.
Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints

« prev Page 46/68 next »