{"total":29,"rows":[{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661,"area":"lr"},{"id":"2505.07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation","created":"2025-05-12","cited_by_count":413,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2505.03318","title":"Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning","created":"2025-05-06","cited_by_count":90,"area":"lr"},{"id":"2510.22319","title":"GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping","created":"2025-10-25","cited_by_count":49,"area":"lr"},{"id":"2505.17618","title":"Scaling Image and Video Generation via Test-Time Evolutionary Search","created":"2025-05-23","cited_by_count":40,"area":"lr"},{"id":"2505.17574","title":"InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO","created":"2025-05-23","cited_by_count":15,"area":"lr"},{"id":"2603.21872","title":"Manifold-Aware Exploration for Reinforcement Learning in Video Generation","created":"2026-03-23","cited_by_count":15,"area":"lr"},{"id":"2512.02622","title":"RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence","created":"2025-12-02","cited_by_count":13,"area":"lr"},{"id":"2510.10518","title":"VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning","created":"2025-10-12","cited_by_count":12,"area":"lr"},{"id":"2605.14278","title":"KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration","created":"2026-05-14","cited_by_count":11,"area":"lr"},{"id":"2511.18719","title":"Seeing What Matters: Visual Preference Policy Optimization for Visual Generation","created":"2025-11-24","cited_by_count":10,"area":"lr"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2512.09924","title":"Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning","created":"2025-12-10","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2512.12387","title":"Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment","created":"2025-12-13","cited_by_count":6,"area":"lr"},{"id":"2511.18919","title":"Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation","created":"2025-11-24","cited_by_count":5,"area":"lr"},{"id":"2605.15980","title":"Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"id":"2606.03183","title":"Inference-Time Scaling for Joint Audio-Video Generation","created":"2026-06-02","cited_by_count":4,"area":"lr"},{"id":"2603.06014","title":"EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation","created":"2026-03-06","cited_by_count":2,"area":"lr"},{"id":"2604.19234","title":"Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.05922","title":"Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2512.03534","title":"Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation","created":"2025-12-03","cited_by_count":1,"area":"lr"},{"id":"2511.05393","title":"PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment","created":"2025-11-07","cited_by_count":0,"area":"lr"},{"id":"2608.05600","title":"LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.29322","title":"Test-Time Scaling for Video Diffusion Models via Diagnosis-Guided Candidate Recycling","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.38377","title":"PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.01973","title":"Token-Level Video Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.12572","title":"DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}