ICML 2026

6,487 papers

Top Research Directions

Research directions most represented by ICML 2026 papers.

Scaling Language Model Reasoning Beyond Verifiable Rewards 79
Group Relative Policy Optimization for Large Reasoning Models 63
General Purpose Reasoning from Specialized Reinforcement Learning 62
Overcoming the Iterative Inference Latency of Diffusion Models 50
Shifting from Static Benchmarks to Dynamic Evaluation 47
Controlling Language Models Through Latent Space Interventions 45
Resolving Superposition with Sparse Autoencoders 42
Autonomous Code Refinement via Execution Feedback Loops 41
The Performance Cliff in Ultra Low Bit Quantization 41
Activation Steering for Inference Time Model Control 39
Mitigating Expert Collapse in Sparse Mixture of Experts 37
Proxy Objective Exploitation in Language Model Alignment 37
The Decoupling of Visual Perception and Logical Reasoning 36
Mitigating Computational Overthinking in Large Reasoning Models 35
Input Adaptive Compute Allocation for Language Models 33

Top Authors

AuthorPapers
Junchi Yan19
Min Zhang19
Tat-Seng Chua15
Haoxuan Li14
Philip Torr14
Yong Li14
Kun Zhang13
Li Shen13
Tianlong Chen13
Xiang Wang13
Xin Geng13
Yejin Choi13
Bo An12
Mihaela van der Schaar12
Xunliang Cai12
Bo Han11
Ge Zhang11
Han Liu11
Jiang Bian11
LEI BAI11

Impactful Papers

Papers from ICML 2026 that shaped research clusters.

Foundational

Papers

Title
Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models
Embodied Task Planning via Graph-Informed Action Generation with Large Language Models
EmBrace: A Collective Knowledge Fusion Framework Toward Unified EEG Foundation Models
E-mem: Multi-Agent Based Episodic Context Reconstruction for LLM Agent Memory
Emergence of Biased Consensus in Multi-Agent LLM Debates
Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
Emergence of Hierarchical Emotion Organization in Large Language Models
Emergent Alignment via Competition
Emergent Analogical Reasoning in Transformers
Emergent Biological Realism in RL-Trained DNA Language Models
Emergent Communication Under Misinformation
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Emergent Visual Representations through Unsupervised Spiking Networks with Synaptic Pruning
EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting
Empirical Gaussian Processes
Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
EmWorld: Emotion World Model with Latent State Evolution for Scenario-Incremental Dynamic Facial Expression Recognition
Endogenous Resistance to Activation Steering in Language Models
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
End-to-End Compression for Tabular Foundation Models
EnerGS: Energy-Based Gaussian Splatting under Partial Geometric Priors
EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors
Energy-based Compositional Diffusion Planning
Energy-Structured Low-Rank Adaptation for Continual Learning
EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions
Enhanced Latent-Space Adversarial Training for Super-Resolution
Enhanced Multi-Instance Partial Label Learning via Average Gradient Outer Product
Enhancing Affine Maximizer Auctions with Correlation-Aware Payment
Enhancing Conformal Prediction via Class Similarity
Enhancing Cross-subject Emotion Recognition via Heterogeneous Distribution Augmentation and Collaborative Learning
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
Enhancing LLM Training via Spectral Clipping
Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
Enhancing Neural Theorem Proving via High-Quality Data Selection and Verifier Feedback
Enhancing Neural Theorem Proving via High-Quality Proof Selection and Verifier Feedback
Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein Embedding
Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
EnsembleVLA: Ensemble Learning for Vision-Language Action Models
Ensembling Sparse Autoencoders
Entangled No More: Multi-Domain Decoupling for Robust Dynamic Graph Neural Networks
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
EntRAG: Entity-Centric Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
EntroKV: Entropy-Guided Dynamic Budget Allocation for KV-Cache Compression
Entropic Mirror Monte Carlo
Entropy-Aware Dynamic KV Cache Sparsification for Autoregressive Image Generation and Editing
Entropy-Aware On-Policy Distillation of Language Models
Entropy-aware Span-Constrained Optimal Transport for Robust Cross-Tokenizer Knowledge Distillation

« prev Page 37/130 next »