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
CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure
CroCoDiLight: Repurposing Cross-View Completion Encoders for Relighting
CRONOS: Continuous time reconstruction for 4D medical longitudinal series
Cross-ControlNet: Training-Free Fusion of Multiple Conditions for Text-to-Image Generation
Cross-Domain Lossy Compression via Rate- and Classification-Constrained Optimal Transport
Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Critics
Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
Cross-Modal Redundancy and the Geometry of Vision–Language Embeddings
CrossPL: Systematic Evaluation of Large Language Models for Cross Programming Language Interoperating Code Generation
Cross-Timestep: 3D Diffusion Model with Trans-temporal Memory LSTM and Adaptive Priori Decoding Strategy for Medical Segmentation
Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation
CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models
CryoNet.Refine: A One-step Diffusion Model for Rapid Refinement of Structural Models with Cryo-EM Density Map Restraints
CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction
CSRv2: Unlocking Ultra-Sparse Embeddings
CTBench: Cryptocurrency Time Series Generation Benchmark
CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
CTRL&SHIFT: High-quality Geometry-Aware Object Manipulation in Visual Generation
Ctrl-World: A Controllable Generative World Model for Robot Manipulation
CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence under Partial Observations
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset
Culture in Action: Evaluating Text-to-Image Models through Social Activities
Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness
CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model
Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence
Curvature-Guided Task Synergy for Skeleton based Temporal Action Segmentation
Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach
Cut Less, Fold More: Model Compression through the Lens of Projection Geometry
Cutting the Skip: Training Residual-Free Transformers
C-Voting: Confidence-Based Test-Time Voting without Explicit Energy Functions
CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
Cyber-Zero: Training Cybersecurity Agents without Runtime
CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling
CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis
d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
DA$^{2}$: Depth Anything in Any Direction
DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
DADA: Dual Averaging with Distance Adaptation
DAG-Math: Graph-of-Thought Guided Mathematical Reasoning in LLMs
DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models
DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS
DanceTogether: Generating Interactive Multi-Person Video without Identity Drifting
Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of Mind
D-AR: Diffusion via Autoregressive Models

« prev Page 20/108 next »