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
Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From Data
SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs
Sleeping Reinforcement Learning
Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning
SlimLLM: Accurate Structured Pruning for Large Language Models
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences
Smooth Interpolation for Improved Discrete Graph Generative Models
SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services
Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration
Softmax is not Enough (for Sharp Size Generalisation)
Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels
Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo
Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound
Solving Satisfiability Modulo Counting Exactly with Probabilistic Circuits
Solving Zero-Sum Convex Markov Games
SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model
Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs
Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
Sounding that Object: Interactive Object-Aware Image to Audio Generation
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
Sparse Autoencoders, Again?
Sparse Autoencoders for Hypothesis Generation
Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
Sparse-pivot: Dynamic correlation clustering for node insertions
Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks
Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
Spatial Reasoning with Denoising Models
SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
Spectral-Aware Reservoir Computing for Fast and Accurate Time Series Classification
Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
Speeding up Policy Simulation in Supply Chain RL
SPEX: Scaling Feature Interaction Explanations for LLMs
Spherical-Nested Diffusion Model for Panoramic Image Outpainting

« prev Page 57/68 next »