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
DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
Dr.LLM: Dynamic Layer Routing in LLMs
Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
D&R: Recovery-based AI-Generated Text Detection via a Single Black-box LLM Call
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
DR-Submodular Maximization with Stochastic Biased Gradients: Classical and Quantum Gradient Algorithms
Drugging the Undruggable: Benchmarking and Modeling Fragment-Based Screening
DrugTrail: Interpretable Drug Discovery via Structured Reasoning and Druggability‑Tailored Preference Optimization
DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
DSA: Efficient Inference For Video Generation Models via Distributed Sparse Attention
DTO-KD: Dynamic Trade-off Optimization for Effective Knowledge Distillation
DTP: Delta-Guided Two Stage Pruning for Mamba-based Multimodal Large Language Models
Dual-Branch Representations with Dynamic Gated Fusion and Triple-Granularity Alignment for Deep Multi-View Clustering
Dual Distillation for Few-Shot Anomaly Detection
DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation
Dual Goal Representations
Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation
Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis
DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving
Dual-objective Language Models: Training Efficiency Without Overfitting
Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations
Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise
Dual-Path Condition Alignment for Diffusion Transformers
Dual Perspectives on Non-Contrastive Self-Supervised Learning
Dual Randomized Smoothing: Beyond Global Noise Variance
Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts
Dual-Scale World Memory for LLM Agents towards Hard-Exploration Problems
Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual Prediction
Dual-Space Smoothness for Robust and Balanced LLM Unlearning
DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher
DUET: Optimizing LLM Training Data Mixtures via Noisy Feedback from Unseen, Downstream Evaluation Tasks
DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization
Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
DVD-Quant: Data-free Video Diffusion Transformers Quantization
DVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
DynaGuard: A Dynamic Guardian Model With User-Defined Policies
Dynamical properties of dense associative memory
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
Dynamic Classifier-Free Diffusion Guidance via Online Feedback
Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
Dynamic Early Exit in Reasoning Models
DynamicInfer: Runtime-Aware Sparse Offloading for LLMs Inference on a Consumer-Grade GPU
Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
Dynamic Multi-sample Mixup with Gradient Exploration for Open-set Graph Anomaly Detection
Dynamic Novel View Synthesis in High Dynamic Range
Dynamic Reflections: Probing Video Representations with Text Alignment
Dynamic Speculative Agent Planning

« prev Page 27/108 next »