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
Identifying and Understanding Cross-Class Features in Adversarial Training
Identifying biological perturbation targets through causal differential networks
Identifying Causal Direction via Variational Bayesian Compression
Identifying Metric Structures of Deep Latent Variable Models
Identifying Neural Dynamics Using Interventional State Space Models
Idiosyncrasies in Large Language Models
iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection
IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic
Imagine While Reasoning in Space: Multimodal Visualization-of-Thought
Imitation Learning by Estimating Expertise of Demonstrators
Imitation Learning from a Single Temporally Misaligned Video
IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling
Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks
Implicit degree bias in the link prediction task
Implicit Language Models are RNNs: Balancing Parallelization and Expressivity
Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
Implicit Riemannian Optimism with Applications to Min-Max Problems
Implicit Subgraph Neural Network
Importance Corrected Neural JKO Sampling
Importance Sampling for Nonlinear Models
Impossible Videos
Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation
Improved and Oracle-Efficient Online $\ell_1$-Multicalibration
Improved and Oracle-Efficient Online ℓ1-Multicalibration
Improved Approximations for Hard Graph Problems using Predictions
Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions
Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization Scheme
Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms
Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling
Improved Off-policy Reinforcement Learning in Biological Sequence Design
Improved Online Confidence Bounds for Multinomial Logistic Bandits
Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance
Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint
Improving Compositional Generation with Diffusion Models Using Lift Scores
Improving Consistency Models with Generator-Augmented Flows
Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
Improving Diversity in Language Models: When Temperature Fails, Change the Loss
Improving Flow Matching by Aligning Flow Divergence
Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
Improving Generalization with Flat Hilbert Bayesian Inference
Improving LLM Safety Alignment with Dual-Objective Optimization
Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens
Improving LLM Video Understanding with 16 Frames Per Second
Improving Memory Efficiency for Training KANs via Meta Learning
Improving Model Alignment Through Collective Intelligence of Open-Source Models
Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques
Improving Multimodal Learning Balance and Sufficiency through Data Remixing

« prev Page 29/68 next »