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
Consistent Text-to-Image Generation via Scene De-Contextualization
Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models
Constant Degree Matrix-Driven Incomplete Multi-View Clustering via Connectivity-Structure and Embedding Tensor Learning
Constantly Improving Image Models Need Constantly Improving Benchmarks
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Constrained Decoding of Diffusion LLMs with Context-Free Grammars
Constrained Diffusion for Protein Design with Hard Structural Constraints
Constraint-guided Hardware-aware NAS through Gradient Modification
Constraint Matters: Multi-Modal Representation for Reducing Mixed-Integer Linear programming
Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
Contact-guided Real2Sim from Monocular Video with Planar Scene Primitives
Contact Wasserstein Geodesics for Non-Conservative Schrödinger Bridges
Contamination Detection for VLMs Using Multi‑Modal Semantic Perturbations
Content-Aware Mamba for Learned Image Compression
Context and Diversity Matter: The Emergence of In-Context Learning in World Models
ContextBench: Modifying Contexts for Targeted Latent Activation and Behaviour Elicitation
ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation
ContextIF: Enhancing Instruction-Following through Context Reward
Context Learning for Multi-Agent Discussion
ContextNav: Towards Agentic Multimodal In-Context Learning
Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning
ContextPRM: Leveraging Contextual Coherence for multi-domain Test-Time Scaling
Context Tokens are Anchors: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective
Contextual and Seasonal LSTMs for Time Series Anomaly Detection
Contextual Causal Bayesian Optimisation
Contextual Multi-Armed Bandits with Minimum Aggregated Revenue Constraints
Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model
Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
Continuous Audio Language Models
Continuous Chain of Thought Enables Parallel Exploration and Reasoning
Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
Continuous multinomial logistic regression for neural decoding
Continuous Space-Time Video Super-Resolution with 3D Fourier Fields
Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
Continuum Transformers Perform In-Context Learning by Operator Gradient Descent
Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells
Contractive Diffusion Policies
Contrastive Diffusion Guidance for Spatial Inverse Problems
Contrastive Predictive Coding Done Right for Mutual Information Estimation
Controllable diffusion-based generation for multi-channel biological data
Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning
Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs
Controllable Sequence Editing for Biological and Clinical Trajectories
Controllable Video Generation with Provable Disentanglement
Controlling Repetition in Protein Language Models
Control Tax: The Price of Keeping AI in Check
Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimization
Convergence Analysis of Tsetlin Machines under Noise-Free and Noisy Training Conditions: From $2$ Bits to $k$ Bits

« prev Page 18/108 next »