{"total":34,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.20751","title":"Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning","created":"2025-08-28","cited_by_count":92,"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":"2512.08153","title":"TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models","created":"2025-12-09","cited_by_count":31,"area":"lr"},{"id":"2510.01982","title":"Fine-Grained GRPO for Precise Preference Alignment in Flow Models","created":"2025-10-02","cited_by_count":21,"area":"lr"},{"id":"2601.20218","title":"DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment","created":"2026-01-28","cited_by_count":21,"area":"lr"},{"id":"2512.21514","title":"DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO","created":"2025-12-25","cited_by_count":17,"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":"2510.21583","title":"Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization","created":"2025-10-24","cited_by_count":14,"area":"lr"},{"id":"2601.00423","title":"E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models","created":"2026-01-01","cited_by_count":14,"area":"lr"},{"id":"2510.02654","title":"Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models","created":"2025-10-03","cited_by_count":12,"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":"2601.05729","title":"TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment","created":"2026-01-09","cited_by_count":10,"area":"lr"},{"id":"2511.18833","title":"PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation","created":"2025-11-24","cited_by_count":9,"area":"lr"},{"id":"2602.06422","title":"Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO","created":"2026-02-06","cited_by_count":9,"area":"lr"},{"id":"2512.00743","title":"Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards","created":"2025-11-30","cited_by_count":8,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2604.23380","title":"V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think","created":"2026-04-25","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":"2512.15347","title":"Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models","created":"2025-12-17","cited_by_count":6,"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":"2603.12648","title":"From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space","created":"2026-03-13","cited_by_count":3,"area":"lr"},{"id":"2604.18518","title":"UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models","created":"2026-04-20","cited_by_count":3,"area":"lr"},{"id":"2605.10937","title":"Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping","created":"2026-05-11","cited_by_count":3,"area":"lr"},{"id":"2607.00535","title":"Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition","created":"2026-07-01","cited_by_count":3,"area":"lr"},{"id":"2603.06623","title":"Advances in GRPO for Generation Models: A Survey","created":"2026-02-21","cited_by_count":2,"area":"lr"},{"id":"2606.06828","title":"AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO","created":"2026-06-05","cited_by_count":2,"area":"lr"},{"id":"2608.03215","title":"GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2510.10201","title":"RLFR: Extending Reinforcement Learning for LLMs with Flow Environment","created":"2025-10-11","cited_by_count":0,"area":"lr"},{"id":"2605.19995","title":"CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2607.17572","title":"JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models","created":"2026-07-20","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":"2609.22041","title":"$\\lambda$-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.38329","title":"ExploreNet: Learning Where to Explore in Diffusion GRPO","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}