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
Boomerang Distillation Enables Zero-Shot Model Size Interpolation
Boosted Trees on a Diet: Compact Models for Resource-Constrained Devices
Boosting Entropy with Bell Box Quantization
Boosting for Predictive Sufficiency
Boosting Medical Visual Understanding From Multi-Granular Language Learning
Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization
Boosting Open Set Recognition Performance through Modulated Representation Learning
Bootstrapping MLLM for Weakly‑Supervised Class‑Agnostic Object Counting
BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity
BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management
BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning
Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
Bound by semanticity: universal laws governing the generalization-identification tradeoff
Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond
Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer
Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
Branch and Bound Search for Exact MAP Inference in Credal Networks
Branched Schrödinger Bridge Matching
BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
Breaking and Fixing Defenses Against Control Flow Hijacking in Multi-Agent Systems
Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?
Breaking Gradient Temporal Collinearity for Robust Spiking Neural Networks
Breaking Safety Paradox with Feasible Dual Policy Iteration
Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution Training
Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors
Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action Set
BRIDGE: Bi-level Reinforcement Learning for Dynamic Group Structure in Coalition Formation Games
BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving
Bridging Degradation Discrimination and Generation for Universal Image Restoration
Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding
Bridging Explainability and Embeddings: BEE Aware of Spuriousness
Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative Models
Bridging Input Feature Spaces Towards Graph Foundation Models
Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
Bridging ML and algorithms: comparison of hyperbolic embeddings
Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
Bridging Piano Transcription and Rendering via Disentangled Score Content and Style
Bridging Radiology and Pathology Foundation Models via Concept-Based Multimodal Co-Adaptation
Bridging Successor Measure and Online Policy Learning with Flow Matching-Based Representations
Bridging the Distribution Gap to Harness Pretrained Diffusion Priors for Super-Resolution
Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
Bridging the performance-gap between target-free and target-based reinforcement learning
Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models
BrowseNet: Graph-Based Associative Memory for Contextual Information Retrieval
BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, and Rerankers
Buckingham $\pi$-Invariant Test‑Time Projection for Robust PDE Surrogate Modeling

« prev Page 12/108 next »