{"total":79,"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":"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":"2508.05606","title":"Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision","created":"2025-08-07","cited_by_count":56,"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":"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":"2509.09680","title":"FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark","created":"2025-09-11","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":"2510.14958","title":"MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning","created":"2025-10-16","cited_by_count":35,"area":"lr"},{"id":"2506.21448","title":"ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing","created":"2025-06-26","cited_by_count":34,"area":"lr"},{"id":"2505.07538","title":"Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning","created":"2025-05-12","cited_by_count":33,"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":"2510.04290","title":"ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation","created":"2025-10-05","cited_by_count":29,"area":"lr"},{"id":"2603.09877","title":"InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing","created":"2026-03-10","cited_by_count":28,"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":"2512.24165","title":"DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models","created":"2025-12-30","cited_by_count":19,"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":"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":"2603.21872","title":"Manifold-Aware Exploration for Reinforcement Learning in Video Generation","created":"2026-03-23","cited_by_count":15,"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":"2512.05112","title":"DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2025-12-04","cited_by_count":13,"area":"lr"},{"id":"2512.23568","title":"ThinkGen: Generalized Thinking for Visual Generation","created":"2025-12-29","cited_by_count":13,"area":"lr"},{"id":"2503.07154","title":"Ideas in Inference-time Scaling can Benefit Generative Pre-training Algorithms","created":"2025-03-10","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":"2602.02437","title":"UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing","created":"2026-02-02","cited_by_count":12,"area":"lr"},{"id":"2605.22344","title":"Bernini: Latent Semantic Planning for Video Diffusion","created":"2026-05-21","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":"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":"2512.04563","title":"COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence","created":"2025-12-04","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":"2603.30043","title":"Video Models Reason Early: Exploiting Plan Commitment for Maze Solving","created":"2026-03-31","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":"2512.24125","title":"Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training","created":"2025-12-30","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":"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":"2510.08157","title":"Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing","created":"2025-10-09","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":"2603.08652","title":"CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2026-03-09","cited_by_count":6,"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":"2604.19730","title":"FASTER: Value-Guided Sampling for Fast RL","created":"2026-04-21","cited_by_count":4,"area":"lr"},{"id":"2507.10768","title":"Spatial Reasoners for Continuous Variables in Any Domain","created":"2025-07-14","cited_by_count":3,"area":"lr"},{"id":"2603.01563","title":"LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2603.01893","title":"Generative Visual Chain-of-Thought for Image Editing","created":"2026-03-02","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":"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":"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":"2605.17850","title":"Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures","created":"2026-05-18","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":"2607.04461","title":"Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models","created":"2026-07-05","cited_by_count":2,"area":"lr"},{"id":"2511.20906","title":"DASIP: Dynamic Test-Time Compute Scaling for Robot Control with Stochastic Interpolant Policies","created":"2025-11-25","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":"2602.07061","title":"TACIT: Transformation-Aware Capturing of Implicit Thought","created":"2026-02-05","cited_by_count":1,"area":"lr"},{"id":"2606.02842","title":"Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoning","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.11498","title":"See like a Robot: Robot-Centric Pointmaps for VLA Models","created":"2026-07-13","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":"2601.20208","title":"TRACER: Texture-Robust Affordance Chain-of-Thought for Deformable-Object Refinement","created":"2026-01-28","cited_by_count":0,"area":"lr"},{"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":"2604.17385","title":"SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning","created":"2026-04-19","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":"2605.21522","title":"Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2606.15188","title":"Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing","created":"2026-06-13","cited_by_count":0,"area":"lr"},{"id":"2607.04750","title":"FM-ChangeNet: Learning Change through Pathwise Feature Transport","created":"2026-07-06","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":"2608.29322","title":"Test-Time Scaling for Video Diffusion Models via Diagnosis-Guided Candidate Recycling","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.22867","title":"Leveraging Inference-Time Compute for Diffusion Models via Global Scheduling of Denoising Trajectories","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.35673","title":"FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36826","title":"Learning via Self-Consistency for Diffusion-based Video Reasoning","created":"2026-09-29","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":"2610.12898","title":"Rethinking the Roles of Diffusion and Decoding: Predictive-State Flows for Parallel Language Generation","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.13316","title":"ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.19871","title":"Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning","created":"2026-10-14","cited_by_count":0,"area":"lr"},{"id":"2610.20331","title":"Are We Overthinking One-Step Generation?","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}