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
SPHINX: Structural Prediction using Hypergraph Inference Network
SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity
SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) Complexity
SpikF: Spiking Fourier Network for Efficient Long-term Prediction
Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution
Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models
SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution
SPRI: Aligning Large Language Models with Context-Situated Principles
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
Square$\chi$PO: Differentially Private and Robust $\chi^2$-Preference Optimization in Offline Direct Alignment
SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images
Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness
Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion
Stabilizing Sample Similarity in Representation via Mitigating Random Consistency
Stable Fair Graph Representation Learning with Lipschitz Constraint
Stable Offline Value Function Learning with Bisimulation-based Representations
Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
Stacey: Promoting Stochastic Steepest Descent via Accelerated ℓp-Smooth Nonconvex Optimization
Staged and Physics-Grounded Learning Framework with Hyperintensity Prior for Pre-Contrast MRI Synthesis
STAIR: Improving Safety Alignment with Introspective Reasoning
STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
Star Attention: Efficient LLM Inference over Long Sequences
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
Statistical Collusion by Collectives on Learning Platforms
Statistical Hypothesis Testing for Auditing Robustness in Language Models
Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise
Statistical Test for Feature Selection Pipelines by Selective Inference
Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning
Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection
STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification
Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
Stealix: Model Stealing via Prompt Evolution
StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
Steerable Transformers for Volumetric Data
Steering Protein Language Models
Steer LLM Latents for Hallucination Detection
Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design
Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
Stochastic Deep Restoration Priors for Imaging Inverse Problems
Stochastic Encodings for Active Feature Acquisition
Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training
Stochastic Online Conformal Prediction with Semi-Bandit Feedback
Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes
Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints
SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics
STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
Strategic A/B testing via Maximum Probability-driven Two-armed Bandit
Strategic Planning: A Top-Down Approach to Option Generation

« prev Page 58/68 next »