{"total":78,"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":"2501.09732","title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","created":"2025-01-16","cited_by_count":234,"area":"lr"},{"id":"2501.06848","title":"A General Framework for Inference-time Scaling and Steering of Diffusion Models","created":"2025-01-12","cited_by_count":224,"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":"2505.21906","title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","created":"2025-05-28","cited_by_count":49,"area":"lr"},{"id":"2505.23614","title":"Inference-time Scaling of Diffusion Models through Classical Search","created":"2025-05-29","cited_by_count":49,"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":"2505.17618","title":"Scaling Image and Video Generation via Test-Time Evolutionary Search","created":"2025-05-23","cited_by_count":40,"area":"lr"},{"id":"2503.19385","title":"Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing","created":"2025-03-25","cited_by_count":38,"area":"lr"},{"id":"2508.09968","title":"Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models","created":"2025-08-13","cited_by_count":35,"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":"2509.21474","title":"d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation","created":"2025-09-25","cited_by_count":27,"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":"2509.21655","title":"DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models","created":"2025-09-25","cited_by_count":23,"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":"2504.15932","title":"Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning","created":"2025-04-22","cited_by_count":18,"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":"2505.17574","title":"InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO","created":"2025-05-23","cited_by_count":15,"area":"lr"},{"id":"2507.18537","title":"TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation","created":"2025-07-24","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":"2501.09012","title":"Multimodal LLMs Can Reason about Aesthetics in Zero-Shot","created":"2025-01-15","cited_by_count":14,"area":"lr"},{"id":"2505.22524","title":"Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design","created":"2025-05-28","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":"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":"2511.18719","title":"Seeing What Matters: Visual Preference Policy Optimization for Visual Generation","created":"2025-11-24","cited_by_count":10,"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":"2505.14036","title":"Adaptive Inference-Time Scaling via Cyclic Diffusion Search","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2507.08390","title":"Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement","created":"2025-07-11","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":"2505.22407","title":"Self-Reflective Reinforcement Learning for Diffusion-based Image Reasoning Generation","created":"2025-05-28","cited_by_count":6,"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":"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":"2603.10395","title":"Graph-GRPO: Training Graph Flow Models with Reinforcement Learning","created":"2026-03-11","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":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","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":"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":"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":"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":"2509.04372","title":"Connections between reinforcement learning with feedback,test-time scaling, and diffusion guidance: An anthology","created":"2025-09-04","cited_by_count":1,"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":"2508.16524","title":"Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning","created":"2025-08-22","cited_by_count":0,"area":"lr"},{"id":"2511.05553","title":"EVLP:Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning","created":"2025-11-03","cited_by_count":0,"area":"lr"},{"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":"2602.19974","title":"RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2603.06140","title":"Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion","created":"2026-03-06","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":"2607.06018","title":"RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures","created":"2026-07-07","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":"2609.38329","title":"ExploreNet: Learning Where to Explore in Diffusion GRPO","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.02774","title":"LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence Generators","created":"2026-10-02","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"},{"id":"2610.17246","title":"LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}