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
CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting
CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
Composable Sparse Subnetworks via Maximum-Entropy Principle
Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
Composer: A Search Framework for Hybrid Neural Architecture Design
Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
Composite Optimization with Error Feedback: the Dual Averaging Approach
Compositional amortized inference for large-scale hierarchical Bayesian models
Compositional-ARC: Assessing Systematic Generalization in Abstract Spatial Reasoning
Compositional Diffusion with Guided search for Long-Horizon Planning
Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning
Compositional Generalization through Gradient Search in Nonparametric Latent Space
Compositional Visual Planning via Inference-Time Diffusion Scaling
Composition-Grounded Data Synthesis for Visual Reasoning
Composition of Memory Experts for Diffusion World Models
Composition of Pretrained Diffusion Models: A Logic-Based Calculus
Computational Bottlenecks for Denoising Diffusions
Compute-Optimal Quantization-Aware Training
Computer Agent Arena: Toward Human-Centric Evaluation and Analysis of Computer-Use Agents
ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
Computing Equilibrium beyond Unilateral Deviation
CoNavBench: Collaborative Long-Horizon Vision-Language Navigation Benchmark
Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks
Concept-based Adversarial Attack: a Probabilistic Perspective
Concepts' Information Bottleneck Models
Concept-TRAK: Understanding how diffusion models learn concepts through concept attribution
CONCUR: A Framework for Continual Constrained and Unconstrained Routing
Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
Conditional Independent Component Analysis for Estimating Causal Structure with Latent Variables
Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting
Conditioned Initialization for Attention
Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss
Condition Matters in Full-head 3D GANs
ConfHit: Conformal Generative Design with Oracle-Free Guarantees
Confident and Adaptive Generative Speech Recognition via Risk Control
Confident Block Diagonal Structure-Aware Invariable Graph Completion for Incomplete Multi-view Clustering
Conformalized Decision Risk Assessment
Conformalized Hierarchical Calibration for Uncertainty-Aware Adaptive Hashing
Conformalized Survival Counterfactuals Prediction for General Right-Censored Data
Conformal Prediction for Long-Tailed Classification
Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
Conformal Robustness Control: A New Strategy for Robust Decision
Conjuring Semantic Similarity
ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types
CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition
ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance Mask
Consis-GCPO: Consistency-Preserving Group Causal Preference Optimization for Vision Customization
Consistency-Driven Calibration and Matching for Few-Shot Class Incremental Learning
Consistent Low-Rank Approximation
Consistent Noisy Latent Rewards for Trajectory Preference Optimization in Diffusion Models

« prev Page 17/108 next »