{"total":17,"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":"2505.14460","title":"VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank","created":"2025-05-20","cited_by_count":79,"area":"lr"},{"id":"2508.06924","title":"AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning","created":"2025-08-09","cited_by_count":22,"area":"lr"},{"id":"2601.20218","title":"DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment","created":"2026-01-28","cited_by_count":21,"area":"lr"},{"id":"2506.05384","title":"Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment","created":"2025-06-03","cited_by_count":14,"area":"lr"},{"id":"2510.08425","title":"Reinforcing Diffusion Models by Direct Group Preference Optimization","created":"2025-10-09","cited_by_count":14,"area":"lr"},{"id":"2510.02880","title":"Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models","created":"2025-10-03","cited_by_count":12,"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":"2509.21871","title":"Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"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":"2607.00535","title":"Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition","created":"2026-07-01","cited_by_count":3,"area":"lr"},{"id":"2508.12628","title":"Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning","created":"2025-08-18","cited_by_count":2,"area":"lr"},{"id":"2604.09704","title":"Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2511.05393","title":"PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment","created":"2025-11-07","cited_by_count":0,"area":"lr"},{"id":"2601.02441","title":"Understanding Pure Textual Reasoning for Blind Image Quality Assessment","created":"2026-01-05","cited_by_count":0,"area":"lr"},{"id":"2603.20785","title":"ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking","created":"2026-03-21","cited_by_count":0,"area":"lr"},{"id":"2609.08316","title":"From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment","created":"2026-09-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}