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
Evolution of Concepts in Language Model Pre-Training
Evolving Graph Structured Programs for Circuit Generation with Large Language Models
EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
Exchangeability of GNN Representations with Applications to Graph Retrieval
Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code
ExGRPO: Learning to Reason from Experience
Exo-Plore: Exploring Exoskeleton Control Space through Human-aligned Simulation
ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning
Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns
Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis
EXP-Bench: Can AI Conduct AI Research Experiments?
Experience-based Knowledge Correction for Robust Planning in Minecraft
Expert Divergence Learning for MoE-based Language Models
Expert Heads: Robust Evidence Identification for Large Language Models
Expertise Can Be Helpful for Reinforcement Learning-based Macro Placement
ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists
Expert Merging in Sparse Mixture of Experts with Nash Bargaining
Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking
ExpGuard: LLM Content Moderation in Specialized Domains
Explainable $ K $-means Neural Networks for Multi-view Clustering
Explainable LLM Unlearning through Reasoning
Explainable Mixture Models through Differentiable Rule Learning
Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation
Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classification
Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
Exploratory Causal Inference in SAEnce
Exploratory Diffusion Model for Unsupervised Reinforcement Learning
Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
Exploring Cross-Modal Flows for Few-Shot Learning
Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts
Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs
Exploring Mode Connectivity in Krylov Subspace for Domain Generalization
Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content
Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection
Exploring State-Space Models for Data-Specific Neural Representations
Exploring Synthesizable Chemical Space with Iterative Pathway Refinements
Exploring the Design Space of Transition Matching
Exploring the Potential of Encoder-free Architectures in 3D LMMs
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
Exponential-Wrapped Mechanisms: Differential Privacy on Hadamard Manifolds Made Practical
Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
Exposing Mixture and Annotating Confusion for Active Universal Test-Time Adaptation
Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems
EXPO: Stable Reinforcement Learning with Expressive Policies
Expressiveness of Multi-Neuron Convex Relaxations in Neural Network Certification
Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling

« prev Page 32/108 next »