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
Efficient Learning of Deep State Space Models via Importance Smoothing
Efficient LLM Moderation with Multi-Layer Latent Prototypes
Efficiently Learning Drifting Halfspaces with Massart Noise
Efficiently Solving Discounted MDPs via Predictions with Unknown Prediction Errors
Efficiently Training Time-to-First-Spike Spiking Neural Networks from Scratch
Efficient Mismatch-Tolerant Coding for Model-Driven Compression
Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate
Efficient Multi-modal Dataset Distillation via Analytic Parameter Matching
Efficient Multi-round LLM Inference over Disaggregated Serving
Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing
Efficient numeracy in language models through single-token number embeddings
Efficient Numeracy in Language Models through Single-Token Number Encodings
Efficient Online Influence Maximization under the Independent Cascade Model with Node-Level Feedback
Efficient Online Variational Estimation via Monte Carlo Sampling
Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models
Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Frames
Efficient Preference Poisoning Attack on Offline RLHF
Efficient privacy loss accounting for subsampling and random allocation
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
Efficient Public Verification of Private ML via Regularization
Efficient Reasoning with Hidden Thinking
Efficient RL Training for LLMs with Experience Replay
Efficient Skill Grounding via Code Refactoring with Small Language Models
Efficient Stochastic Optimisation via Sequential Monte Carlo
Efficient Synthetic Network Generation via Latent Embedding Reconstruction
Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
Efficient Test-time Inference for Generative Planning Models with OCL Search
Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing
Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization
Efficient Transformer Attention for SNNs via Hadamard Simplification
Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets
EGG: An Expert-Guided Agent Framework for Kernel Generation
Ego3S: Select, Strengthen, and Synchronize for Efficient Egocentric Reasoning
EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video
EigenCache: Rethinking Diffusion Acceleration as Covariance-Optimal Forecasting and Submodular Information Allocation
Eigenvectors of Experts are Training-free Non-collapsing Routers
Ekka: Automated Diagnosis of Silent Errors in LLM Inference
Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
Elastic Diffusion Transformer
ElicitR: Unlocking Latent Reasoning in Dense Retrievers via Generative Regularization
Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learned Force Fields
Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force Fields
Eliminating Solution Bias in Differentially Private Optimization
Ellipsoidal Time Series Forecasting
Embedding Hybrid Systems into Continuous Latent Vector Fields
Embedding-perturbed Exploration Preference Optimization for Flow Models
Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
Embodied-DETR: End-to-End Temporal 3D Object Detection in Egocentric Views

« prev Page 36/130 next »