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
Efficient Skill Discovery via Regret-Aware Optimization
Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization
Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
e-GAI: e-value-based Generalized $\alpha$-Investing for Online False Discovery Rate Control
EgoPrivacy: What Your First-Person Camera Says About You?
EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation
Ehrenfeucht-Haussler Rank and Chain of Thought
Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time
ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
Eliciting Language Model Behaviors with Investigator Agents
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces
ELoRA: Low-Rank Adaptation for Equivariant GNNs
Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers
Elucidating the design space of language models for image generation
Elucidating the Design Space of Multimodal Protein Language Models
Embedding Safety into RL: A New Take on Trust Region Methods
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective
Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
Emergent Response Planning in LLMs
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph
Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection
Emotional Face-to-Speech
Empirical Privacy Variance
Empowering World Models with Reflection for Embodied Video Prediction
Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks
Enabling Optimal Decisions in Rehearsal Learning under CARE Condition
ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks
EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption
End-to-End Learning Framework for Solving Non-Markovian Optimal Control
Energy-Based Flow Matching for Generating 3D Molecular Structure
Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
Enforcing Idempotency in Neural Networks
Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
Enhancing Decision-Making of Large Language Models via Actor-Critic
Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
Enhancing Foundation Models with Federated Domain Knowledge Infusion
Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of Invariance
Enhancing Graph Invariant Learning from a Negative Inference Perspective
Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization

« prev Page 19/68 next »