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
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
Scaling Inference-Efficient Language Models
Scaling Large Motion Models with Million-Level Human Motions
Scaling Laws for Differentially Private Language Models
Scaling Laws for Floating Point Quantization Training
Scaling Laws for Floating-Point Quantization Training
Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
Scaling Laws for Pre-training Agents and World Models
Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
Scaling Laws for Upcycling Mixture-of-Experts Language Models
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
Scaling Probabilistic Circuits via Monarch Matrices
Scaling Sparse Feature Circuits For Studying In-Context Learning
Scaling Test-Time Compute Without Verification or RL is Suboptimal
Scaling Trends in Language Model Robustness
Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields
Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear Solvers
sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models
SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification
Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
Score Matching with Missing Data
Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning
SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
SE(3)-Equivariant Diffusion Policy in Spherical Fourier Space
SEAD: Unsupervised Ensemble of Streaming Anomaly Detectors
Secant Line Search for Frank-Wolfe Algorithms
SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games
SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning
Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation
Selective Prediction via Training Dynamics
Selective Preference Aggregation
Selective Prompt Anchoring for Code Generation
Selective Response Strategies for GenAI
Self-Bootstrapping for Versatile Test-Time Adaptation
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
Self-Consistency Preference Optimization
Self-Consuming Generative Models with Adversarially Curated Data
Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
Self-Discriminative Modeling for Anomalous Graph Detection

« prev Page 55/68 next »