{"total":61,"rows":[{"id":"2509.25050","title":"Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models","created":"2025-09-29","cited_by_count":67,"area":"diffusion"},{"id":"2512.24146","title":"Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning","created":"2025-12-30","cited_by_count":18,"area":"diffusion"},{"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":"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":"2511.16955","title":"Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models","created":"2025-11-21","cited_by_count":16,"area":"alignment"},{"id":"2601.10332","title":"Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders","created":"2026-01-15","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":"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":"2602.17025","title":"WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning","created":"2026-02-19","cited_by_count":12,"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":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2605.15458","title":"Video Models Can Reason with Verifiable Rewards","created":"2026-05-14","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":"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":"2604.04142","title":"OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models","created":"2026-04-05","cited_by_count":7,"area":"diffusion"},{"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":"2602.03425","title":"ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning","created":"2026-02-03","cited_by_count":6,"area":"deeprl"},{"id":"2604.15311","title":"LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories","created":"2026-04-16","cited_by_count":6,"area":"diffusion"},{"id":"2512.13303","title":"ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement","created":"2025-12-15","cited_by_count":5,"area":null},{"id":"2601.12401","title":"Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation","created":"2026-01-18","cited_by_count":5,"area":"deeprl"},{"id":"2602.06825","title":"AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models","created":"2026-02-06","cited_by_count":5,"area":"diffusion"},{"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":"2605.15803","title":"Embedding-perturbed Exploration Preference Optimization for Flow Models","created":"2026-05-15","cited_by_count":5,"area":"alignment"},{"id":"2512.22170","title":"SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models","created":"2025-12-17","cited_by_count":4,"area":"alignment"},{"id":"2601.15968","title":"HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models","created":"2026-01-22","cited_by_count":4,"area":"diffusion"},{"id":"2603.17461","title":"AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization","created":"2026-03-18","cited_by_count":4,"area":"diffusion"},{"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":"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":"2604.06916","title":"FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling","created":"2026-04-08","cited_by_count":3,"area":"diffusion"},{"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":"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":"2608.23664","title":"Scaling Reinforcement Learning for Diffusion Models via Velocity Matching","created":"2026-08-24","cited_by_count":3,"area":"diffusion"},{"id":"2601.02356","title":"Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes","created":"2026-01-05","cited_by_count":2,"area":"deeprl"},{"id":"2603.06623","title":"Advances in GRPO for Generation Models: A Survey","created":"2026-02-21","cited_by_count":2,"area":"lr"},{"id":"2604.19009","title":"Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning","created":"2026-04-21","cited_by_count":2,"area":"diffusion"},{"id":"2605.19804","title":"Stitched Value Model for Diffusion Alignment","created":"2026-05-19","cited_by_count":2,"area":"alignment"},{"id":"2606.02218","title":"Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing","created":"2026-06-01","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":"2511.22146","title":"C$^2$DLM: Causal Concept-Guided Diffusion Large Language Models","created":"2025-11-27","cited_by_count":1,"area":"diffusion"},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.25661","title":"DRM: Diffusion-based Reward Model With Step-wise Guidance","created":"2026-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2605.26013","title":"AdvantageFlow: Advantage-Weighted Least Squares for RL in Flow Models","created":"2026-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2605.28691","title":"OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning","created":"2026-05-27","cited_by_count":1,"area":"diffusion"},{"id":"2609.04282","title":"Step Back to Move Forward: Reflection-Aware Preference Optimization for Visual Generation","created":"2026-09-03","cited_by_count":1,"area":"diffusion"},{"id":"2609.09905","title":"FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models","created":"2026-09-09","cited_by_count":1,"area":"diffusion"},{"id":"2605.27736","title":"Explicit Critic Guidance for Aligning Diffusion Models","created":"2026-05-26","cited_by_count":0,"area":"diffusion"},{"id":"2606.00228","title":"LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching","created":"2026-05-29","cited_by_count":0,"area":"diffusion"},{"id":"2606.19004","title":"Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training","created":"2026-06-17","cited_by_count":0,"area":"diffusion"},{"id":"2607.07693","title":"Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF","created":"2026-07-08","cited_by_count":0,"area":"alignment"},{"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":"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":"2609.38329","title":"ExploreNet: Learning Where to Explore in Diffusion GRPO","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.01789","title":"iADD: Improving Alignment and Diversity in Diffusion Policy Optimization","created":"2026-10-01","cited_by_count":0,"area":"diffusion"},{"id":"2610.05252","title":"MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation","created":"2026-10-04","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}