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
Characterizing Pattern Matching and Its Limits on Compositional Task Structures
Characterizing the Discrete Geometry of ReLU Networks
Chart Deep Research in LVLMs via Parallel Relative Policy Optimization
ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
Charts Are Not Images: On the Challenges of Scientific Chart Editing
Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
CheckMate! Watermarking Graph Diffusion Models in Polynomial Time
ChemEval: A Multi-level and Fine-grained Chemical Capability Evaluation for Large Language Models
Chessformer: A Unified Architecture for Chess Modeling
Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
Choices Speak Louder than Questions
CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction
ChronoEdit: Towards Temporal Reasoning for In-Context Image Editing and World Simulation
ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks
Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns
CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration
CIMemories: A Compositional Benchmark For Contextual Integrity In LLMs
CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models
Circuit Insights: Towards Interpretability Beyond Activations
CircuitNet 3.0: A Multi-Modal Dataset with Task-Oriented Augmentation for AI-Driven Circuit Design
CircuitSense: A Hierarchical MLLM Benchmark Bridging Visual Comprehension and Symbolic Reasoning in Engineering Design Process
Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models
CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing
CitySeeker: How Do VLMs Explore Embodied Urban Navigation with Implicit Human Needs?
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
CLARC: C/C++ Benchmark for Robust Code Search
ClarifyVC: Clarifying Ambiguous Commands in Vehicle Control with a Hybrid Data Augmentation Pipeline
CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering
CL-DPS: A Contrastive Learning Approach to Blind Nonlinear Inverse Problem Solving via Diffusion Posterior Sampling
CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk
CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally
CLIP-FMoE: Scalable CLIP via Fused Mixture-of-Experts with Enforced Specialization
Clipped Gradient Methods for Nonsmooth Convex Optimization under Heavy-Tailed Noise: A Refined Analysis
CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting
CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions
Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ bias
Closing the Gap Between Text and Speech Understanding in LLMs
Closing the Modality Gap Aligns Group-Wise Semantics
Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models
CLUE: Conflict-guided Localization for LLM Unlearning Framework
Clustering by Denoising: Latent plug-and-play diffusion for single-cell embeddings
CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild
CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics
CMT-Benchmark: A Benchmark for Condensed Matter Theory Built by Expert Researchers
CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow-Map Models
CoAct-1: Computer-using Multi-agent System with Coding Actions
Coarse-to-Fine Learning of Dynamic Causal Structures

« prev Page 15/108 next »