Image de couverture de livre

Fine-Grained GRPO for Precise Preference Alignment in Flow Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Yujie, Ling, Pengyang, Bu, Jiazi, Wang, Yibin, Zang, Yuhang, Wang, Jiaqi, Niu, Li, Zhai, Guangtao
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
par: Wang, Yibin, et autres
Publié: (2025)

DiCache: Let Diffusion Model Determine Its Own Cache
par: Bu, Jiazi, et autres
Publié: (2025)

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
par: Bu, Jiazi, et autres
Publié: (2026)

Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
par: Ling, Pengyang, et autres
Publié: (2026)

Unified Personalized Reward Model for Vision Generation
par: Wang, Yibin, et autres
Publié: (2026)

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
par: Bu, Jiazi, et autres
Publié: (2025)

Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier
par: Zhou, Yujie, et autres
Publié: (2026)

ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way
par: Bu, Jiazi, et autres
Publié: (2024)

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
par: Zhou, Yujie, et autres
Publié: (2025)

MotionClone: Training-Free Motion Cloning for Controllable Video Generation
par: Ling, Pengyang, et autres
Publié: (2024)

UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation
par: Wang, Yibin, et autres
Publié: (2025)

Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
par: Wang, Yibin, et autres
Publié: (2025)

Unified Reward Model for Multimodal Understanding and Generation
par: Wang, Yibin, et autres
Publié: (2025)

BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling
par: Yang, Jiachen, et autres
Publié: (2026)

EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models
par: Dai, Xuanlang, et autres
Publié: (2026)

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
par: Zhao, Xiangyu, et autres
Publié: (2025)

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment
par: Deng, Haoyou, et autres
Publié: (2026)

Visual-RFT: Visual Reinforcement Fine-Tuning
par: Liu, Ziyu, et autres
Publié: (2025)

TempFlow-GRPO: When Timing Matters for GRPO in Flow Models
par: He, Xiaoxuan, et autres
Publié: (2025)

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
par: Cui, Chenhang, et autres
Publié: (2024)

OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models
par: Zhang, Liyu, et autres
Publié: (2026)

Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning
par: Chen, Hanmo, et autres
Publié: (2026)

ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorization
par: Lao, Danning, et autres
Publié: (2024)

Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate
par: Huang, Qidong, et autres
Publié: (2024)

SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
par: Zhang, Zhixiong, et autres
Publié: (2026)

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
par: Liu, Ziyu, et autres
Publié: (2024)

Visual Agentic Reinforcement Fine-Tuning
par: Liu, Ziyu, et autres
Publié: (2025)

Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing
par: Li, Jinsong, et autres
Publié: (2026)

2nd Place Report of MOSEv2 Challenge 2025: Concept Guided Video Object Segmentation via SeC
par: Zhang, Zhixiong, et autres
Publié: (2025)

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
par: Wang, Austin, et autres
Publié: (2026)

ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing
par: Jin, Ying, et autres
Publié: (2024)

Unified Scene Representation and Reconstruction for 3D Large Language Models
par: Chu, Tao, et autres
Publié: (2024)

TIT-Score: Evaluating Long-Prompt Based Text-to-Image Alignment via Text-to-Image-to-Text Consistency
par: Wang, Juntong, et autres
Publié: (2025)

Long-CLIP: Unlocking the Long-Text Capability of CLIP
par: Zhang, Beichen, et autres
Publié: (2024)

Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment
par: Gao, Shiqi, et autres
Publié: (2026)

GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning
par: Xu, Yanchen, et autres
Publié: (2025)

Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models
par: Wang, Wei, et autres
Publié: (2024)

Flow-GRPO: Training Flow Matching Models via Online RL
par: Liu, Jie, et autres
Publié: (2025)

MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation
par: Tong, Haibo, et autres
Publié: (2025)

Streaming Long Video Understanding with Large Language Models
par: Qian, Rui, et autres
Publié: (2024)