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
Partially Observable Reinforcement Learning with Memory Traces
Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data
PASS: Private Attributes Protection with Stochastic Data Substitution
PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
Patch-wise Structural Loss for Time Series Forecasting
PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs
PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations
PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity
PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction
Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data
PENCIL: Long Thoughts with Short Memory
PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion
Perception in Reflection
Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
Perceptually Constrained Precipitation Nowcasting Model
Peri-LN: Revisiting Normalization Layer in the Transformer Architecture
Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive Querying
Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data
Permutation Equivariant Neural Networks for Symmetric Tensors
Permutation-Free High-Order Interaction Tests
Persistent Topological Features in Large Language Models
PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction
Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning
PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis
Pfeife: Automatic Pipeline Parallelism for PyTorch
PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness
Phase transitions for the existence of unregularized M-estimators in single index models
Physics Aware Neural Networks for Unsupervised Binding Energy Prediction
Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification
Physics-Informed Generative Modeling of Wireless Channels
Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
Physics-Informed Weakly Supervised Learning For Interatomic Potentials
PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary Learning
PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals
PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
PILAF: Optimal Human Preference Sampling for Reward Modeling
Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule
PINNsAgent: Automated PDE Surrogation with Large Language Models
PIPA: Preference Alignment as Prior-Informed Statistical Estimation
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop
Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models
Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
Pixel-level Certified Explanations via Randomized Smoothing
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference

« prev Page 45/68 next »