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
DANCE: Dual Unbiased Expansion with Group-acquired Alignment for Out-of-distribution Graph Fairness Learning
DataDecide: How to Predict Best Pretraining Data with Small Experiments
Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects
Data-Driven Selection of Instrumental Variables for Additive Nonlinear, Constant Effects Models
Dataflow-Guided Neuro-Symbolic Language Models for Type Inference
Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development
Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models
David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training
DCBM: Data-Efficient Visual Concept Bottleneck Models
DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
DEALing with Image Reconstruction: Deep Attentive Least Squares
De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
Decision-aware Training of Spatiotemporal Forecasting Models to Select a Top-K Subset of Sites for Intervention
Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets
Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making
Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents
Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
Decomposition of Graphic Design with Unified Multimodal Model
De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs
Decoupled SGDA for Games with Intermittent Strategy Communication
Deep Bayesian Filter for Bayes-Faithful Data Assimilation
DeepCrossAttention: Supercharging Transformer Residual Connections
Deep Electromagnetic Structure Design Under Limited Evaluation Budgets
Deep Fuzzy Multi-view Learning for Reliable Classification
DeepLayout: Learning Neural Representations of Circuit Placement Layout
Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer
Deep Neural Cellular Potts Models
Deep Neural Network Piration without Accuracy Loss
Deep Principal Support Vector Machines for Nonlinear Sufficient Dimension Reduction
Deep Reinforcement Learning from Hierarchical Preference Design
Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines
Deep Streaming View Clustering
Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions
Deep Unsupervised Hashing via External Guidance
DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts
Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision
DeFoG: Discrete Flow Matching for Graph Generation
Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph
Deliberation in Latent Space via Differentiable Cache Augmentation
Delta Decompression for MoE-based LLMs Compression
De-mark: Watermark Removal in Large Language Models
Demeaned Sparse: Efficient Anomaly Detection by Residual Estimate
Demonstration Selection for In-Context Learning via Reinforcement Learning
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs.
Demystifying Long Chain-of-Thought Reasoning
Demystifying Singular Defects in Large Language Models
Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation
Dendritic Localized Learning: Toward Biologically Plausible Algorithm

« prev Page 14/68 next »