{"total":28,"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":"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":"2605.15190","title":"RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO","created":"2026-05-14","cited_by_count":7,"area":"diffusion"},{"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":"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":"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":"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":"2605.12112","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":"2604.19009","title":"Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning","created":"2026-04-21","cited_by_count":2,"area":"diffusion"},{"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":"2605.25661","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":"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}