{"total":56,"rows":[{"id":"2509.16117","title":"DiffusionNFT: Online Diffusion Reinforcement with Forward Process","created":"2025-09-19","cited_by_count":230,"area":"diffusion"},{"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":"2512.21514","title":"DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO","created":"2025-12-25","cited_by_count":17,"area":"lr"},{"id":"2512.24138","title":"GARDO: Reinforcing Diffusion Models without Reward Hacking","created":"2025-12-30","cited_by_count":17,"area":"diffusion"},{"id":"2510.25889","title":"$\\pi_\\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models","created":"2025-10-29","cited_by_count":16,"area":"vla"},{"id":"2512.16906","title":"VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization","created":"2025-12-18","cited_by_count":16,"area":null},{"id":"2603.21872","title":"Manifold-Aware Exploration for Reinforcement Learning in Video Generation","created":"2026-03-23","cited_by_count":15,"area":"lr"},{"id":"2607.07675","title":"Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence","created":"2026-07-08","cited_by_count":15,"area":"moe"},{"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":"2602.12205","title":"DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing","created":"2026-02-12","cited_by_count":14,"area":null},{"id":"2603.23500","title":"UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation","created":"2026-03-24","cited_by_count":13,"area":"diffusion"},{"id":"2511.20256","title":"The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation","created":"2025-11-25","cited_by_count":12,"area":"alignment"},{"id":"2511.21135","title":"SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation","created":"2025-11-26","cited_by_count":12,"area":null},{"id":"2602.12529","title":"Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models","created":"2026-02-13","cited_by_count":12,"area":"diffusion"},{"id":"2603.28718","title":"Stepwise Credit Assignment for GRPO on Flow-Matching Models","created":"2026-03-30","cited_by_count":10,"area":"diffusion"},{"id":"2511.22982","title":"Ovis-Image Technical Report","created":"2025-11-28","cited_by_count":8,"area":null},{"id":"2605.26108","title":"Reinforcing Few-step Generators via Reward-Tilted Distribution Matching","created":"2026-05-25","cited_by_count":8,"area":"diffusion"},{"id":"2512.04784","title":"PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling","created":"2025-12-02","cited_by_count":7,"area":"alignment"},{"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":"2604.17415","title":"Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models","created":"2026-04-19","cited_by_count":7,"area":"diffusion"},{"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":"2605.15190","title":"RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO","created":"2026-05-14","cited_by_count":7,"area":"diffusion"},{"id":"2609.11929","title":"SenseNova-U1.5: Towards Native Unified Visual Intelligence","created":"2026-09-10","cited_by_count":7,"area":"distill"},{"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":"2602.03425","title":"ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning","created":"2026-02-03","cited_by_count":6,"area":"deeprl"},{"id":"2603.02083","title":"$\\pi$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs","created":"2026-03-02","cited_by_count":6,"area":"vla"},{"id":"2606.11025","title":"Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models","created":"2026-06-09","cited_by_count":6,"area":"diffusion"},{"id":"2608.26105","title":"VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning","created":"2026-08-26","cited_by_count":6,"area":"lr"},{"id":"2603.14128","title":"Diffusion Reinforcement Learning via Centered Reward Distillation","created":"2026-03-14","cited_by_count":5,"area":"diffusion"},{"id":"2604.25427","title":"A Systematic Post-Train Framework for Video Generation","created":"2026-04-28","cited_by_count":5,"area":"diffusion"},{"id":"2608.03316","title":"Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging","created":"2026-08-04","cited_by_count":5,"area":"diffusion"},{"id":"2509.25774","title":"PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2605.10983","title":"TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment","created":"2026-05-09","cited_by_count":4,"area":"diffusion"},{"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":"2606.28016","title":"TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL","created":"2026-06-26","cited_by_count":4,"area":"diffusion"},{"id":"2605.07503","title":"Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers","created":"2026-05-08","cited_by_count":3,"area":"diffusion"},{"id":"2605.12112","title":"When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy","created":"2026-05-12","cited_by_count":3,"area":"diffusion"},{"id":"2605.23522","title":"Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models","created":"2026-05-22","cited_by_count":3,"area":"diffusion"},{"id":"2606.19990","title":"Reward as An Agent for Embodied World Models","created":"2026-06-18","cited_by_count":3,"area":"wm"},{"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":"2603.00159","title":"FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation","created":"2026-02-25","cited_by_count":1,"area":"alignment"},{"id":"2603.18528","title":"Correlation-Weighted Multi-Reward Optimization for Compositional Generation","created":"2026-03-19","cited_by_count":1,"area":"alignment"},{"id":"2604.10962","title":"ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching","created":"2026-04-13","cited_by_count":1,"area":"diffusion"},{"id":"2604.28126","title":"AdvDMD: Adversarial Reward Meets DMD For High-Quality Few-Step Generation","created":"2026-04-29","cited_by_count":1,"area":"diffusion"},{"id":"2607.02291","title":"Optimizing Visual Generative Models via Distribution-wise Rewards","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"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":"2608.15139","title":"StructRL: Structured Action-Space Exploration for Flow-Based VLAs","created":"2026-08-15","cited_by_count":1,"area":"vla"},{"id":"2606.00228","title":"LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching","created":"2026-05-29","cited_by_count":0,"area":"diffusion"},{"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":"2609.03528","title":"LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL","created":"2026-09-03","cited_by_count":0,"area":"deeprl"},{"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":"2609.34658","title":"CapField-OPD: Learning Continuous Capability Fields via Joint-Anchored Multi-Teacher On-Policy Distillation for Flow Models","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.37372","title":"Think Before You Score: Thinking Reward Model for Visual Generation","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2609.38329","title":"ExploreNet: Learning Where to Explore in Diffusion GRPO","created":"2026-09-29","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}