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
Beyond Speedup - Utilizing KV Cache for Sampling and Reasoning
Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models
Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffraction
Beyond Student: An Asymmetric Network for Neural Network Inheritance
Beyond Text-Only: Towards Multimodal Table Retrieval in Open-World
Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model
Beyond the Heatmap: A Rigorous Evaluation of Component Impact in MCTS-Based TSP Solvers
Beyond the Known: An Unknown-Aware Large Language Model for Open-Set Text Classification
Beyond Uniformity: Regularizing Implicit Neural Representations through a Lipschitz Lens
Beyond Uniformity: Sample and Frequency Meta Weighting for Post-Training Quantization of Diffusion Models
Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
Beyond Visual Reconstruction Quality: Object Perception-aware 3D Gaussian Splatting for Autonomous Driving
BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation
BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning
BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation
Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
Bi-Criteria Metric Distortion
BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
Bidirectional Predictive Coding
BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations
Bilateral Information-aware Test-time Adaptation for Vision-Language Models
Bilevel Optimization with Lower-Level Uniform Convexity: Theory and Algorithm
Bilinear representation mitigates reversal curse and enables consistent model editing
Bi-Lipschitz Autoencoder With Injectivity Guarantee
Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation
BioBO: Biology-informed Bayesian Optimization for Perturbation Design
BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models
Biologically Plausible Learning via Bidirectional Spike-Based Distillation
BioMD: All-atom Generative Model for Biomolecular Dynamics Simulation
BioTamperNet: Affinity-Guided State-Space Model Detecting Tampered Biomedical Images
BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals
Birch SGD: A Tree Graph Framework for Local and Asynchronous SGD Methods
BIRD: Behavior Induction via Representation-structure Distillation
BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions
Bird's-eye-view Informed Reasoning Driver
Black-Box Privacy Attacks on Shared Representations in Multitask Learning
BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation
Block Recurrent Dynamics in Vision Transformers
Block-Sample MAC-Bayes Generalization Bounds
Block-wise Adaptive Caching for Accelerating Diffusion Policy
BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization
BoGrape: Bayesian optimization over graphs with shortest-path encoded
BOLT: Decision‑Aligned Distillation and Budget-Aware Routing for Constrained Multimodal QA on Robots
Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems
Boolean Satisfiability via Imitation Learning

« prev Page 11/108 next »