{"total":84,"rows":[{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661,"area":"lr"},{"id":"2505.07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation","created":"2025-05-12","cited_by_count":413,"area":"lr"},{"id":"2507.21802","title":"MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE","created":"2025-07-29","cited_by_count":178,"area":"diffusion"},{"id":"2508.04324","title":"TempFlow-GRPO: When Timing Matters for GRPO in Flow Models","created":"2025-08-06","cited_by_count":97,"area":"lr"},{"id":"2509.06040","title":"BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models","created":"2025-09-07","cited_by_count":61,"area":"diffusion"},{"id":"2406.10208","title":"Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering","created":"2024-06-14","cited_by_count":48,"area":null},{"id":"2502.01051","title":"Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization","created":"2025-02-03","cited_by_count":37,"area":"diffusion"},{"id":"2506.03517","title":"DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models","created":"2025-06-04","cited_by_count":34,"area":"diffusion"},{"id":"2410.07171","title":"IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation","created":"2024-10-09","cited_by_count":33,"area":"diffusion"},{"id":"2509.06942","title":"Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference","created":"2025-09-08","cited_by_count":30,"area":"diffusion"},{"id":"2410.03190","title":"Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization","created":"2024-10-04","cited_by_count":26,"area":"diffusion"},{"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":"2511.20549","title":"Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning","created":"2025-11-25","cited_by_count":17,"area":"diffusion"},{"id":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","cited_by_count":15,"area":"alignment"},{"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":"2511.19217","title":"ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment","created":"2025-11-24","cited_by_count":13,"area":"alignment"},{"id":"2603.23500","title":"UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation","created":"2026-03-24","cited_by_count":13,"area":"diffusion"},{"id":"2411.11727","title":"Aligning Few-Step Diffusion Models with Dense Reward Difference Learning","created":"2024-11-18","cited_by_count":12,"area":"diffusion"},{"id":"2508.21016","title":"Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance","created":"2025-08-28","cited_by_count":10,"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":"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":"2505.22569","title":"ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models","created":"2025-05-28","cited_by_count":8,"area":"diffusion"},{"id":"2505.11070","title":"Towards Self-Improvement of Diffusion Models via Group Preference Optimization","created":"2025-05-16","cited_by_count":7,"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":"2506.23138","title":"VisualPrompter: Semantic-Aware Prompt Optimization with Visual Feedback for Text-to-Image Synthesis","created":"2025-06-29","cited_by_count":6,"area":null},{"id":"2507.11554","title":"Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models","created":"2025-07-14","cited_by_count":6,"area":"diffusion"},{"id":"2511.18050","title":"UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios","created":"2025-11-22","cited_by_count":6,"area":"diffusion"},{"id":"2512.22288","title":"Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model","created":"2025-12-25","cited_by_count":6,"area":"lr"},{"id":"2601.08587","title":"MoCha:End-to-End Video Character Replacement without Structural Guidance","created":"2026-01-13","cited_by_count":6,"area":null},{"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":"2505.22008","title":"Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences","created":"2025-05-28","cited_by_count":5,"area":"diffusion"},{"id":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"area":null},{"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":"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":"2603.12575","title":"AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation","created":"2026-03-13","cited_by_count":4,"area":"diffusion"},{"id":"2603.18991","title":"CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think","created":"2026-03-19","cited_by_count":4,"area":"diffusion"},{"id":"2604.24952","title":"Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization","created":"2026-04-27","cited_by_count":4,"area":"alignment"},{"id":"2510.18353","title":"Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback","created":"2025-10-21","cited_by_count":3,"area":"diffusion"},{"id":"2512.19479","title":"Emotion-Director: Bridging Affective Shortcut in Emotion-Oriented Image Generation","created":"2025-12-22","cited_by_count":3,"area":"diffusion"},{"id":"2602.00413","title":"Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation","created":"2026-01-31","cited_by_count":3,"area":"diffusion"},{"id":"2602.18799","title":"Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance","created":"2026-02-21","cited_by_count":3,"area":"diffusion"},{"id":"2602.19631","title":"Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection","created":"2026-02-23","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":"2511.01450","title":"Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation","created":"2025-11-03","cited_by_count":2,"area":"alignment"},{"id":"2512.23426","title":"Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision","created":"2025-12-29","cited_by_count":2,"area":"diffusion"},{"id":"2602.05202","title":"GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modeling","created":"2026-02-05","cited_by_count":2,"area":"mllm"},{"id":"2602.19180","title":"VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery","created":"2026-02-22","cited_by_count":2,"area":"alignment"},{"id":"2603.00918","title":"Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards","created":"2026-03-01","cited_by_count":2,"area":"alignment"},{"id":"2604.24953","title":"ViPO: Visual Preference Optimization at Scale","created":"2026-04-27","cited_by_count":2,"area":"alignment"},{"id":"2605.12179","title":"SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning","created":"2026-05-12","cited_by_count":2,"area":"alignment"},{"id":"2605.19804","title":"Stitched Value Model for Diffusion Alignment","created":"2026-05-19","cited_by_count":2,"area":"alignment"},{"id":"2605.28615","title":"Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization","created":"2026-05-27","cited_by_count":2,"area":"alignment"},{"id":"2505.19196","title":"CoCA: Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning","created":"2025-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2511.22242","title":"Rethinking Test Time Scaling for Flow-Matching Generative Models","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2512.22175","title":"Characterizing Motion Encoding in Video Diffusion Timesteps","created":"2025-12-18","cited_by_count":1,"area":"diffusion"},{"id":"2601.04300","title":"Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes","created":"2026-01-07","cited_by_count":1,"area":"diffusion"},{"id":"2603.20828","title":"EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis","created":"2026-03-21","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":"2607.02291","title":"Optimizing Visual Generative Models via Distribution-wise Rewards","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2609.07072","title":"Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection","created":"2026-09-07","cited_by_count":1,"area":null},{"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":"2502.06023","title":"Dual Caption Preference Optimization for Diffusion Models","created":"2025-02-09","cited_by_count":0,"area":"diffusion"},{"id":"2509.04126","title":"MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation","created":"2025-09-04","cited_by_count":0,"area":"diffusion"},{"id":"2512.22681","title":"CritiFusion: Semantic Critique and Spectral Alignment for Faithful Text-to-Image Generation","created":"2025-12-27","cited_by_count":0,"area":"diffusion"},{"id":"2601.22495","title":"Gradual Fine-Tuning for Flow Matching Models","created":"2026-01-30","cited_by_count":0,"area":"diffusion"},{"id":"2602.03208","title":"Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2605.19839","title":"When Preference Labels Fall Short: Aligning Diffusion Models from Real Data","created":"2026-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2605.27736","title":"Explicit Critic Guidance for Aligning Diffusion Models","created":"2026-05-26","cited_by_count":0,"area":"diffusion"},{"id":"2605.30038","title":"Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models","created":"2026-05-28","cited_by_count":0,"area":"diffusion"},{"id":"2606.21498","title":"Balancing Performance and Diversity in GRPO Autoregressive Text-to-Image Post-Training","created":"2026-06-19","cited_by_count":0,"area":"lr"},{"id":"2607.06609","title":"D2PO: Optimizing Diffusion Samplers via Dynamic Preference","created":"2026-07-07","cited_by_count":0,"area":"diffusion"},{"id":"2607.26647","title":"Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time","created":"2026-07-29","cited_by_count":0,"area":"diffusion"},{"id":"2608.08487","title":"RenderMatte: Exact-Alpha Rendering and Group-Relative Alignment for Image Matting","created":"2026-08-09","cited_by_count":0,"area":null},{"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":"2608.20011","title":"Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking","created":"2026-08-20","cited_by_count":0,"area":"diffusion"},{"id":"2609.03688","title":"ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion Models","created":"2026-09-03","cited_by_count":0,"area":"diffusion"},{"id":"2609.13425","title":"ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement","created":"2026-09-11","cited_by_count":0,"area":"diffusion"},{"id":"2609.34528","title":"Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34673","title":"FestDPO: Few-step Generator Alignment with Direct Preference Optimization","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.04980","title":"Geometry-Aware Preference Optimization for Text-to-Image Diffusion Models","created":"2026-10-04","cited_by_count":0,"area":"diffusion"},{"id":"2610.09015","title":"Personalize at Test Time: Learning User Preferences for Image Generation","created":"2026-10-06","cited_by_count":0,"area":"diffusion"},{"id":"2610.19563","title":"SaTPO: Text-to-Image Safety Alignment via Transition Preference Optimization","created":"2026-10-14","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}