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
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
Fixed-Confidence Multiple Change Point Identification under Bandit Feedback
Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function
Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
FLAM: Frame-Wise Language-Audio Modeling
FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials
Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
FlatQuant: Flatness Matters for LLM Quantization
Fleet of Agents: Coordinated Problem Solving with Large Language Models
Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation
Flexibility-conditioned protein structure design with flow matching
Flexible and Efficient Grammar-Constrained Decoding
Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning
Flexible Tails for Normalizing Flows
FlexiClip: Locality-Preserving Free-Form Character Animation
FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
FlipAttack: Jailbreak LLMs via Flipping
Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
FloE: On-the-Fly MoE Inference on Memory-constrained GPU
Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
Flow-based Domain Randomization for Learning and Sequencing Robotic Skills
FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields
Flow-field inference from neural data using deep recurrent networks
Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
Flow Matching for Denoised Social Recommendation
Flow Matching for Few-Trial Neural Adaptation with Stable Latent Dynamics
Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
Flow Q-Learning
Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models
Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025
Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages
FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization
Fragments to Facts: Partial-Information Fragment Inference from LLMs
FrameBridge: Improving Image-to-Video Generation with Bridge Models
Fraud-Proof Revenue Division on Subscription Platforms
FreeMesh: Boosting Mesh Generation with Coordinates Merging
Free Process Rewards without Process Labels
Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models

« prev Page 23/68 next »