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
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data
Local Identifying Causal Relations in the Presence of Latent Variables
Locality Preserving Markovian Transition for Instance Retrieval
Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning
Local Pan-privacy for Federated Analytics
LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D
Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
Logarithmic Regret for Online KL-Regularized Reinforcement Learning
Logits are All We Need to Adapt Closed Models
LOGO --- Long cOntext aliGnment via efficient preference Optimization
Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning
Long-Form Speech Generation with Spoken Language Models
LongRoPE2: Near-Lossless LLM Context Window Scaling
Long-Short Alignment for Effective Long-Context Modeling in LLMs
Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Looking Beyond the Top-1: Transformers Determine Top Tokens in Order
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)
Loss Functions and Operators Generated by f-Divergences
LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression
Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization
Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits
Low-Rank Adapting Models for Sparse Autoencoders
Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression
Low-Rank Thinning
LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers
LSCD: Lomb--Scargle Conditioned Diffusion for Time series Imputation
LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models
M2PDE: Compositional Generative Multiphysics and Multi-component PDE Simulation
M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture
Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics
Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
Mahalanobis++: Improving OOD Detection via Feature Normalization
Maintaining Proportional Committees with Dynamic Candidate Sets
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic
MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models
MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

« prev Page 36/68 next »