Image de couverture de livre

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Deng, Haoyou, Yan, Keyu, Mao, Chaojie, Wang, Xiang, Liu, Yu, Gao, Changxin, Sang, Nong
Format:	Preprint
Publié:	2026
Sujets:	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

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

Learning Unpaired Image Dehazing with Physics-based Rehazy Generation
par: Deng, Haoyou, et autres
Publié: (2025)

High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network
par: Zhang, Feng, et autres
Publié: (2025)

REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence
par: Zheng, Ruochen, et autres
Publié: (2024)

DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios
par: Jiao, Siyi, et autres
Publié: (2024)

Diffusion Model for Dense Matching
par: Nam, Jisu, et autres
Publié: (2023)

Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets
par: Zuo, Jialong, et autres
Publié: (2025)

Structural Pruning via Spatial-aware Information Redundancy for Semantic Segmentation
par: Wu, Dongyue, et autres
Publié: (2024)

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

From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper
par: Li, Ling, et autres
Publié: (2026)

HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation
par: Zhang, Huaxin, et autres
Publié: (2023)

FlowR: Flowing from Sparse to Dense 3D Reconstructions
par: Fischer, Tobias, et autres
Publié: (2025)

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
par: Tong, Yunze, et autres
Publié: (2026)

UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation
par: Wang, Xiang, et autres
Publié: (2024)

HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation
par: Wang, Xiaolong, et autres
Publié: (2024)

Efficient Sparse-to-Dense Visual Localization via Compact Gaussian Scene Representation and Accelerated Dense Pose Estimation
par: Li, Zizhuo, et autres
Publié: (2026)

Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration
par: Wu, Dongyue, et autres
Publié: (2025)

Object-Aware Video Matting with Cross-Frame Guidance
par: Zhang, Huayu, et autres
Publié: (2025)

Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
par: Yin, Wenti, et autres
Publié: (2025)

Dense-SfM: Structure from Motion with Dense Consistent Matching
par: Lee, JongMin, et autres
Publié: (2025)

TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization
par: Jing, Xuepeng, et autres
Publié: (2026)

SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
par: Xu, Zhengze, et autres
Publié: (2023)

Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models
par: Yu, Benjamin, et autres
Publié: (2025)

BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning
par: Ding, Ning, et autres
Publié: (2026)

CLIP-guided Prototype Modulating for Few-shot Action Recognition
par: Wang, Xiang, et autres
Publié: (2023)

Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed
par: Wang, Yifan, et autres
Publié: (2024)

Dense Semantic Matching with VGGT Prior
par: Yang, Songlin, et autres
Publié: (2025)

ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
par: Zuo, Jialong, et autres
Publié: (2025)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
par: Song, Enxin, et autres
Publié: (2023)

DOMR: Establishing Cross-View Segmentation via Dense Object Matching
par: Liao, Jitong, et autres
Publié: (2025)

Open-Vocabulary Semantic Segmentation with Image Embedding Balancing
par: Shan, Xiangheng, et autres
Publié: (2024)

Adaptive Prototype Replay for Class Incremental Semantic Segmentation
par: Zhu, Guilin, et autres
Publié: (2024)

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
par: Wang, Xiang, et autres
Publié: (2025)

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

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

RoMa: Robust Dense Feature Matching
par: Edstedt, Johan, et autres
Publié: (2023)

From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting
par: Huang, Zhiwei, et autres
Publié: (2025)

Taming Consistency Distillation for Accelerated Human Image Animation
par: Wang, Xiang, et autres
Publié: (2025)

DenseSR: Image Shadow Removal as Dense Prediction
par: Lin, Yu-Fan, et autres
Publié: (2025)

Dense Matchers for Dense Tracking
par: Jelínek, Tomáš, et autres
Publié: (2024)