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
Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
Breaking the Barrier of Hard Samples: A Data-Centric Approach to Synthetic Data for Medical Tasks
Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning
Breaking the n1.5 Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive Queries
BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
Bridging Fairness and Efficiency in Conformal Inference: A Surrogate-Assisted Group-Clustered Approach
Bridging Layout and RTL: Knowledge Distillation based Timing Prediction
Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models
Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
B-score: Detecting biases in large language models using response history
BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach
BSLoRA: Enhancing the Parameter Efficiency of LoRA with Intra-Layer and Inter-Layer Sharing
BSO: Binary Spiking Online Optimization Algorithm
Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning
C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning
C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention
CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
Calibrated Language Models and How to Find Them with Label Smoothing
Calibrated Physics-Informed Uncertainty Quantification
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
Calibrating Video Watch-time Predictions with Credible Prototype Alignment
CALM: Consensus-Aware Localized Merging for Multi-Task Learning
Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Example
Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios?
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
Can Large Language Models Understand Intermediate Representations in Compilers?
CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
Can Transformers Learn Full Bayesian Inference in Context?
Can Transformers Reason Logically? A Study in SAT Solving
Can We Predict Performance of Large Models across Vision-Language Tasks?
Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy
Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation
CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
Catching Two Birds with One Stone: Reward Shaping with Dual Random Networks for Balancing Exploration and Exploitation
Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models
CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models

« prev Page 9/68 next »