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
Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design
Optimizing Temperature for Language Models with Multi-Sample Inference
Optimizing Test-Time Compute via Meta Reinforcement Finetuning
OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference
OR-Bench: An Over-Refusal Benchmark for Large Language Models
OrcaLoca: An LLM Agent Framework for Software Issue Localization
Organize the Web: Constructing Domains Enhances Pre-Training Data Curation
Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models
Origin Identification for Text-Guided Image-to-Image Diffusion Models
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference
Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
Oscillation-Reduced MXFP4 Training for Vision Transformers
OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction
Otter: Generating Tests from Issues to Validate SWE Patches
Outlier-Aware Post-Training Quantization for Discrete Graph Diffusion Models
Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models
Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner
Overcoming Non-monotonicity in Transducer-based Streaming Generation
Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan
Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization
Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling
Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination’s Impact on Machine Translation
Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling
Overtrained Language Models Are Harder to Fine-Tune
OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition
OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models
OW-VAP: Visual Attribute Parsing for Open World Object Detection
PAC-Bayes Analysis for Recalibration in Classification
PAC Learning with Improvements
Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare Classes
PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs
P(all-atom) Is Unlocking New Path For Protein Design
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
PaperBench: Evaluating AI’s Ability to Replicate AI Research
ParallelComp: Parallel Long-Context Compressor for Length Extrapolation
Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models
Parameter-Efficient Fine-Tuning of State Space Models
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
Parametric Scaling Law of Tuning Bias in Conformal Prediction
Pareto-frontier Entropy Search with Variational Lower Bound Maximization
Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
Pareto-Optimal Fronts for Benchmarking Symbolic Regression Algorithms
Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
PARQ: Piecewise-Affine Regularized Quantization
Parrot: Multilingual Visual Instruction Tuning

« prev Page 44/68 next »