ICLR 2026

5,370 papers

Top Research Directions

Research directions most represented by ICLR 2026 papers.

Scaling Language Model Reasoning Beyond Verifiable Rewards 88
Group Relative Policy Optimization for Large Reasoning Models 81
General Purpose Reasoning from Specialized Reinforcement Learning 79
Shifting from Static Benchmarks to Dynamic Evaluation 66
The Decoupling of Visual Perception and Logical Reasoning 51
Mitigating the Inference Latency of Chain of Thought 50
Activation Steering for Inference Time Model Control 41
Preventing Entropy Collapse in Reinforcement Learning 41
Inference Time Compute Scaling for Complex Reasoning 38
Reinforcement Learning with Verifiable Rewards 38
Autonomous Code Refinement via Execution Feedback Loops 38
Mitigating Computational Overthinking in Large Reasoning Models 37
Resolving Superposition with Sparse Autoencoders 34
Role Specialization in Multi-Agent Architectures 34
The Spatial Reasoning Bottleneck in Multimodal Models 33

Top Authors

AuthorPapers
Fei Huang20
Ge Zhang19
Jianye HAO19
Dahua Lin17
Junchi Yan17
Michael M. Bronstein17
Yejin Choi17
James Y. Zou16
James Zou16
Bo Han15
Jingren Zhou15
Min Zhang15
Tat-Seng Chua15
Caiming Xiong14
Dawn Song14
Pengfei Wan14
Yi Yang14
Jiaheng Liu13
Kai Chen13
Pengjun Xie13

Impactful Papers

Papers from ICLR 2026 that shaped research clusters.

Foundational

Papers

Title
CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer
CoDA: Agentic Systems for Collaborative Data Visualization
CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction
Code Aesthetics with Agentic Reward Feedback
CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model
Code Driven Planning with Domain-Adaptive Selector
CodeGenGuard: A Watermark for Code Generation Models
CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts
CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning
Code World Models for General Game Playing
Codified Finite-state Machines for Role-playing
CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation
CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation
CoFact: Conformal Factuality Guarantees for Language Models under Covariate Shift
CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
CogMoE: Signal-Quality–Guided Multimodal MoE for Cognitive Load Prediction
CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density
CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval
Cognitive models can reveal interpretable value trade-offs in language models
CoLA: Co-Calibrated Logit Adjustment for Long-Tailed Semi-Supervised Learning
COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential Recommendation
CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer
Co-LoRA: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients
COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences
CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
Combination-of-Experts with Knowledge Sharing for Cross-Task Vehicle Routing Problems
Combinatorial Bandit Bayesian Optimization for Tensor Outputs
Combinatorial Rising Bandits
CoMem: Compositional Concept-Graph Memory for Vision–Language Adaptation
ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes
COMI: Coarse-to-fine Context Compression via Marginal Information Gain
CoMind: Towards Community-Driven Agents for Machine Learning Engineering
Command-V: Training-Free Representation Finetuning Transfer
Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training
Communication-Efficient Decentralized Optimization via Double-Communication Symmetric ADMM
Compactness and Consistency: A Conjoint Framework for Deep Graph Clustering
Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
Comparing the learning dynamics of in-context learning and fine-tuning in language models
CompassNav: Steering From Path Imitation to Decision Understanding In Navigation
COMPASS: Robust Feature Conformal Prediction for Medical Segmentation Metrics
ComPhy: Composing Physical Models with end-to-end Alignment
Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks
Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
Complexity- and Statistics-Guided Anomaly Detection in Time Series Foundation Models

« prev Page 16/108 next »