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
Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection
EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference
Eating for a Sustainable Planet: Personalized Sustainable Diet Recommendation via Constraint-Aware Decision-Making Modeling
ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization
ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
EchoAttention: Exploiting Token-Pair Redundancy and Frame-Block Similarity for Efficient Video Generation
ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
EchoRL: Reinforcement Learning via Rollout Echoing
ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots
ECO: Quantized Training without Full-Precision Master Weights
EcoVLA: Environment-Aware Adaptive Pruning with Interleaved Inference Orchestration for Vision-Language-Action Models
ECSEL: Explainable Classification via Signomial Equation Learning
EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning
Edge-colored Clustering in Hypergraphs: A MaxECC Approximation
Editable Proof Sketch for Automated Theorem Proving
Edit-Based Refinement for Parallel Masked Diffusion Language Models
EduMirror: Modeling Educational Social Dynamics with Value-driven Multi-agent Simulation
EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature Experts
EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models
EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment
Effective Distillation to Hybrid xLSTM Architectures
Effective Model Pruning : Measuring the Redundancy of Model Components
Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
Effective Reasoning Chains Reduce Intrinsic Dimensionality
Effects of Structural Reward Shaping on Biophysical Properties in RL-Trained Plasmid Generators
EffGen: Enabling Small Language Models as Capable Autonomous Agents
Efficient Adaptive Testing via Gradient Path Matching Subset Selection for AI Education
Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers
Efficient and Safe Molecular Assembly via Reinforcement Learning and Constraint Solving
Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning
Efficient Bayesian Inference from Noisy Pairwise Comparisons
Efficient Bilevel Optimization for CKA-Guided MoE Upcycling
Efficient Code Analysis via Graph Representation Learning-Guided Large Language Models
Efficient Continuous-Depth Modeling with GRU Equivalents
Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing
Efficient Diffusion Models via Time Step Optimization with Consistent Training and Inference Constraints
Efficient Distributed MLLM Training with Cornstarch
Efficient Distributionally Robust Assortment Optimization in MNL Bandits
Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
Efficient DP-SGD for LLMs with Randomized Clipping
Efficient Equivariant High-Order Crystal Tensor Prediction via Cartesian Local-Environment Many-Body Coupling
Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching
Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads
Efficient Inference for Noisy LLM-as-a-Judge Evaluation
Efficient Learned Image Compression without Entropy Coding

« prev Page 35/130 next »