{"total":78,"rows":[{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"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":"2508.20751","title":"Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning","created":"2025-08-28","cited_by_count":92,"area":"lr"},{"id":"2510.22319","title":"GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping","created":"2025-10-25","cited_by_count":49,"area":"lr"},{"id":"2505.17017","title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO","created":"2025-05-22","cited_by_count":31,"area":"lr"},{"id":"2512.08153","title":"TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models","created":"2025-12-09","cited_by_count":31,"area":"lr"},{"id":"2505.17540","title":"RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning","created":"2025-05-23","cited_by_count":23,"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":"2510.01982","title":"Fine-Grained GRPO for Precise Preference Alignment in Flow Models","created":"2025-10-02","cited_by_count":21,"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":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"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":"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":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2508.11538","title":"Reinforcing Video Reasoning Segmentation to Think Before It Segments","created":"2025-08-15","cited_by_count":15,"area":"lr"},{"id":"2509.25027","title":"STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"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":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","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":"2510.13418","title":"Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation","created":"2025-10-15","cited_by_count":14,"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":"2512.23568","title":"ThinkGen: Generalized Thinking for Visual Generation","created":"2025-12-29","cited_by_count":13,"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":"2601.03467","title":"ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing","created":"2026-01-06","cited_by_count":12,"area":"lr"},{"id":"2605.14278","title":"KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration","created":"2026-05-14","cited_by_count":11,"area":"lr"},{"id":"2511.18719","title":"Seeing What Matters: Visual Preference Policy Optimization for Visual Generation","created":"2025-11-24","cited_by_count":10,"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":"2511.16669","title":"Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO","created":"2025-11-20","cited_by_count":9,"area":"lr"},{"id":"2511.18833","title":"PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation","created":"2025-11-24","cited_by_count":9,"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":"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":"2510.01010","title":"ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning","created":"2025-10-01","cited_by_count":7,"area":"lr"},{"id":"2512.09924","title":"Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning","created":"2025-12-10","cited_by_count":7,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2602.07458","title":"SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning","created":"2026-02-07","cited_by_count":7,"area":"lr"},{"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":"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":"2512.15347","title":"Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models","created":"2025-12-17","cited_by_count":6,"area":"lr"},{"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":"2608.26105","title":"VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning","created":"2026-08-26","cited_by_count":6,"area":"lr"},{"id":"2510.17937","title":"UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts","created":"2025-10-20","cited_by_count":5,"area":"lr"},{"id":"2511.18919","title":"Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation","created":"2025-11-24","cited_by_count":5,"area":"lr"},{"id":"2607.03748","title":"Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process","created":"2026-07-04","cited_by_count":5,"area":"lr"},{"id":"2511.00066","title":"Sharpness-Guided Group Relative Policy Optimization via Probability Shaping","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2603.27866","title":"Wan-R1: Verifiable-Reinforcement Learning for Video Reasoning","created":"2026-03-29","cited_by_count":4,"area":"lr"},{"id":"2605.12495","title":"AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward","created":"2026-05-12","cited_by_count":4,"area":"lr"},{"id":"2605.15980","title":"Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"id":"2602.07533","title":"Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models","created":"2026-02-07","cited_by_count":3,"area":"lr"},{"id":"2603.06032","title":"StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision","created":"2026-03-06","cited_by_count":3,"area":"lr"},{"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":"2604.18518","title":"UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models","created":"2026-04-20","cited_by_count":3,"area":"lr"},{"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":"2605.15198","title":"ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2606.02578","title":"Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling","created":"2026-06-01","cited_by_count":3,"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":"2603.06623","title":"Advances in GRPO for Generation Models: A Survey","created":"2026-02-21","cited_by_count":2,"area":"lr"},{"id":"2604.19234","title":"Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.05922","title":"Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling","created":"2026-05-07","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":"2606.26872","title":"SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing","created":"2026-06-25","cited_by_count":2,"area":"lr"},{"id":"2511.22242","title":"Rethinking Test Time Scaling for Flow-Matching Generative Models","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2602.03102","title":"Consensus Group Relative Policy Optimization for Text Generation","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2605.28388","title":"Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2607.21619","title":"Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimization","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2510.10201","title":"RLFR: Extending Reinforcement Learning for LLMs with Flow Environment","created":"2025-10-11","cited_by_count":0,"area":"lr"},{"id":"2605.07334","title":"RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.19995","title":"CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2607.12800","title":"UniVR: Thinking in Visual Space for Unified Visual Reasoning","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"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":"2608.05600","title":"LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"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":"2610.01973","title":"Token-Level Video Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.12572","title":"DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}