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
KGMark: A Diffusion Watermark for Knowledge Graphs
KinDEL: DNA-Encoded Library Dataset for Kinase Inhibitors
KIND: Knowledge Integration and Diversion for Training Decomposable Models
Kinetic Langevin Diffusion for Crystalline Materials Generation
Knowledge-Guided Wasserstein Distributionally Robust Optimization
Knowledge Retention in Continual Model-Based Reinforcement Learning
Knowledge Swapping via Learning and Unlearning
Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication Optimization
KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis
KoopSTD: Reliable Similarity Analysis between Dynamical Systems via Approximating Koopman Spectrum with Timescale Decoupling
KV Shifting Attention Enhances Language Modeling
KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
Label Distribution Propagation-based Label Completion for Crowdsourcing
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation
LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
Language Models as Implicit Tree Search
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
Language Models over Canonical Byte-Pair Encodings
Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection
LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
Large Continual Instruction Assistant
Large Displacement Motion Transfer with Unsupervised Anytime Interpolation
Large Language-Geometry Model: When LLM meets Equivariance
Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems
Large Language Models are Demonstration Pre-Selectors for Themselves
Large Language Models to Diffusion Finetuning
Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?
LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence
La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation
LASER: Attention with Exponential Transformation
LAST SToP for Modeling Asynchronous Time Series
Latent Action Learning Requires Supervision in the Presence of Distractors
Latent Diffusion Planning for Imitation Learning
Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing
Latent Mamba Operator for Partial Differential Equations
Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data
Latent Thought Models with Variational Bayes Inference-Time Computation
Latent Variable Causal Discovery under Selection Bias
Latent Variable Estimation in Bayesian Black-Litterman Models
LAuReL: Learned Augmented Residual Layer
Layer by Layer: Uncovering Hidden Representations in Language Models
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models

« prev Page 32/68 next »