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
From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning
From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline
From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash Equilibrium
From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms
From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set
From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
From Language Models over Tokens to Language Models over Characters
From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
From Logits to Hierarchies: Hierarchical Clustering made Simple
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models
From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering
From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers
From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs
From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining
From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control
From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation
FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting
Fully Distributed Online Training of Graph Neural Networks in Networked Systems
Fully Dynamic Embedding into $\ell_p$ Spaces
Fully Dynamic Embedding into ℓp Spaces
Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time
Fully Heteroscedastic Count Regression with Deep Double Poisson Networks
FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
Functional Alignment Can Mislead: Examining Model Stitching
Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces
Function-Space Learning Rates
Function-to-Style Guidance of LLMs for Code Translation
Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton
Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks
Fusing Reward and Dueling Feedback in Stochastic Bandits
G-Adaptivity: optimised graph-based mesh relocation for finite element methods
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition
Gandalf the Red: Adaptive Security for LLMs
GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
Gap-Dependent Bounds for Federated $Q$-Learning
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
Gaussian Mixture Flow Matching Models
GaussMark: A Practical Approach for Structural Watermarking of Language Models
GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
GCAL: Adapting Graph Models to Evolving Domain Shifts

« prev Page 24/68 next »