{"total":67,"rows":[{"id":"2510.16888","title":"Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback","created":"2025-10-19","cited_by_count":79,"area":"alignment"},{"id":"2605.10759","title":"Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models","created":"2026-05-11","cited_by_count":19,"area":"diffusion"},{"id":"2602.04663","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design","created":"2026-02-04","cited_by_count":17,"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":"2603.23500","title":"UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation","created":"2026-03-24","cited_by_count":13,"area":"diffusion"},{"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":"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":"2605.26108","title":"Reinforcing Few-step Generators via Reward-Tilted Distribution Matching","created":"2026-05-25","cited_by_count":8,"area":"diffusion"},{"id":"2603.07700","title":"TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward","created":"2026-03-08","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":"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":"2605.21573","title":"Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models","created":"2026-05-20","cited_by_count":6,"area":null},{"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":"2606.11087","title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","created":"2026-06-09","cited_by_count":6,"area":"offlinerl"},{"id":"2603.12893","title":"Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models","created":"2026-03-13","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":"2606.27608","title":"Qwen-Image-2.0-RL Technical Report","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"id":"2607.15273","title":"MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators","created":"2026-07-16","cited_by_count":5,"area":null},{"id":"2510.00502","title":"Diffusion Alignment as Variational Expectation-Maximization","created":"2025-10-01","cited_by_count":4,"area":"diffusion"},{"id":"2602.01591","title":"Faster and Better Alignment for Flow Matching Models via Step-aware Advantages","created":"2026-02-02","cited_by_count":4,"area":"diffusion"},{"id":"2605.11480","title":"Efficient Adjoint Matching for Fine-tuning Diffusion Models","created":"2026-05-12","cited_by_count":4,"area":"diffusion"},{"id":"2511.15208","title":"Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zones","created":"2025-11-19","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":"2605.26552","title":"Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2608.14430","title":"Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View","created":"2026-08-14","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":"2603.06623","title":"Advances in GRPO for Generation Models: A Survey","created":"2026-02-21","cited_by_count":2,"area":"lr"},{"id":"2604.12652","title":"PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning","created":"2026-04-14","cited_by_count":2,"area":"mllm"},{"id":"2604.19009","title":"Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning","created":"2026-04-21","cited_by_count":2,"area":"diffusion"},{"id":"2608.09233","title":"DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models","created":"2026-08-10","cited_by_count":2,"area":"diffusion"},{"id":"2609.00061","title":"ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration","created":"2026-08-30","cited_by_count":2,"area":null},{"id":"2602.12155","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","created":"2026-02-12","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":"2605.26491","title":"Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models","created":"2026-05-26","cited_by_count":1,"area":"diffusion"},{"id":"2606.11075","title":"Exploring the Design Space of Reward Backpropagation for Flow Matching","created":"2026-06-09","cited_by_count":1,"area":"diffusion"},{"id":"2606.17043","title":"Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2607.29025","title":"Evaluation-Verification Reward for Consistent Multi-Reference Image Editing","created":"2026-07-31","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":"2608.21740","title":"CounterAlign: Counterfactual Supervision for Vision-Language-Action Models","created":"2026-08-22","cited_by_count":1,"area":"vla"},{"id":"2608.22780","title":"Can We Perform Online RL for Image Editing without Editing Rewards?","created":"2026-08-24","cited_by_count":1,"area":"alignment"},{"id":"2608.26872","title":"Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher","created":"2026-08-27","cited_by_count":1,"area":"diffusion"},{"id":"2608.28010","title":"When Can Conditional Flow Matching Replace Pointwise Negative Log-Likelihood?","created":"2026-08-28","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":"2609.31882","title":"DOHF: Online Diffusion Fine-tuning with Doob's $h$-transform Guidance","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2603.24936","title":"TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization","created":"2026-03-26","cited_by_count":0,"area":"lr"},{"id":"2605.27736","title":"Explicit Critic Guidance for Aligning Diffusion Models","created":"2026-05-26","cited_by_count":0,"area":"diffusion"},{"id":"2606.12072","title":"World Model Self-Distillation: Training World Models to Solve General Tasks","created":"2026-06-10","cited_by_count":0,"area":"wm"},{"id":"2606.27771","title":"NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning","created":"2026-06-26","cited_by_count":0,"area":"diffusion"},{"id":"2607.11886","title":"Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation","created":"2026-07-13","cited_by_count":0,"area":"alignment"},{"id":"2608.09226","title":"RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.00189","title":"Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.03528","title":"LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL","created":"2026-09-03","cited_by_count":0,"area":"deeprl"},{"id":"2609.30840","title":"Aligning One-Step Generative Models with Reward-Weighted Transport Distillation","created":"2026-09-25","cited_by_count":0,"area":"alignment"},{"id":"2609.32056","title":"Graph Forward Distribution Matching for Molecular Inverse Design","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32236","title":"RoboFFT: Finetuning generative robot policy via online reinforcement learning with forward process","created":"2026-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2609.32665","title":"Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL","created":"2026-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2609.33444","title":"Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"deeprl"},{"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":"2609.37670","title":"MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03423","title":"OuroReward: Sequential Reward Scheduling for Reinforcement Learning in Text-to-3D Generation","created":"2026-10-02","cited_by_count":0,"area":"alignment"},{"id":"2610.05954","title":"MEND: RL For Flow Models via Proximal Velocity Matching","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.12572","title":"DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.14852","title":"Getting Space Right: Agentic Rewards for Image Generation","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.18142","title":"FlowCred: Hierarchical Credit Assignment and Functional Coordination for Joint Text-to-Video Post-Training","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19783","title":"Reinforcement Learning via Advantage Guidance","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}