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
The Role of Sparsity for Length Generalization in LLMs
The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport
The surprising agreement between convex optimization theory and learning-rate scheduling for large model training
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
The Underlying Universal Statistical Structure of Natural Datasets
The Value of Prediction in Identifying the Worst-Off
Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks
Thinking LLMs: General Instruction Following with Thought Generation
Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making
Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset
Tight and Fast Bounds for Multi-Label Learning
Tightening Causal Bounds via Covariate-Aware Optimal Transport
Tilted Sharpness-Aware Minimization
Time-Aware World Model for Adaptive Prediction and Control
TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting
TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting
TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state
Time Series Representations with Hard-Coded Invariances
TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting
TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision
Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation
TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging
TLLC: Transfer Learning-based Label Completion for Crowdsourcing
TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction
To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
Token Coordinated Prompt Attention is Needed for Visual Prompting
Tokenized Bandit for LLM Decoding and Alignment
Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
ToMA: Token Merge with Attention for Diffusion Models
Tool Unlearning for Tool-Augmented LLMs
TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
Topological Signatures of Adversaries in Multimodal Alignments
Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph
Topology-aware Neural Flux Prediction Guided by Physics
TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks

« prev Page 62/68 next »