Image de couverture de livre

Stable Velocity: A Variance Perspective on Flow Matching

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Donglin, Zhang, Yongxing, Yu, Xin, Hou, Liang, Tao, Xin, Wan, Pengfei, Qi, Xiaojuan, Liao, Renjie
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

SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups
par: Zhang, Yongxing, et autres
Publié: (2024)

QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution
par: Yang, Donglin, et autres
Publié: (2025)

MTV-Inpaint: Multi-Task Long Video Inpainting
par: Yang, Shiyuan, et autres
Publié: (2025)

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
par: Cheng, Junhao, et autres
Publié: (2026)

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
par: Yang, Ling, et autres
Publié: (2024)

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
par: Ji, Sihui, et autres
Publié: (2025)

The Velocity Deficit: Initial Energy Injection for Flow Matching
par: Li, Linze, et autres
Publié: (2026)

Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
par: Xian, Jia Jun Cheng, et autres
Publié: (2025)

Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings
par: Hou, Liang, et autres
Publié: (2025)

Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO
par: Cheng, Junhao, et autres
Publié: (2025)

VMoBA: Mixture-of-Block Attention for Video Diffusion Models
par: Wu, Jianzong, et autres
Publié: (2025)

TrajFlow: Multi-modal Motion Prediction via Flow Matching
par: Yan, Qi, et autres
Publié: (2025)

VeCoR -- Velocity Contrastive Regularization for Flow Matching
par: Hong, Zong-Wei, et autres
Publié: (2025)

MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation
par: Fu, Yuxiang, et autres
Publié: (2025)

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
par: Li, Ouxiang, et autres
Publié: (2025)

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

Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
par: Chen, Shengzhe, et autres
Publié: (2026)

SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
par: Ge, Xingtong, et autres
Publié: (2025)

How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach
par: Chang, Chirui, et autres
Publié: (2024)

UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
par: Jiao, Guanlong, et autres
Publié: (2025)

Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Sampling
par: Ma, Zhiyuan, et autres
Publié: (2025)

Creating Blank Canvas Against AI-enabled Image Forgery
par: Song, Qi, et autres
Publié: (2025)

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
par: Ji, Sihui, et autres
Publié: (2025)

GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content Creation
par: Dai, Peng, et autres
Publié: (2024)

Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion
par: Yang, Shiyuan, et autres
Publié: (2024)

CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective
par: Zhu, Wencheng, et autres
Publié: (2024)

IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
par: Xu, Gangwei, et autres
Publié: (2024)

MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization
par: Qi, Lei, et autres
Publié: (2022)

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
par: Liang, Zhanhao, et autres
Publié: (2026)

Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching
par: Hu, Xin, et autres
Publié: (2026)

CLAP: Concave Linear APproximation for Quadratic Graph Matching
par: Liang, Yongqing, et autres
Publié: (2024)

Decoupling Complexity from Scale in Latent Diffusion Model
par: Zhong, Tianxiong, et autres
Publié: (2025)

Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection
par: Zhao, Shizhen, et autres
Publié: (2025)

"Principal Components" Enable A New Language of Images
par: Wen, Xin, et autres
Publié: (2025)

Vision Foundation Models as Generalist Tokenizers for Image Generation
par: Zheng, Anlin, et autres
Publié: (2026)

Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
par: Xia, Qianxin, et autres
Publié: (2026)

Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpening
par: Cao, Zihan, et autres
Publié: (2025)

Temporal Pair Consistency for Variance-Reduced Flow Matching
par: Maduabuchi, Chika, et autres
Publié: (2026)

One Flight Over the Gap: A Survey from Perspective to Panoramic Vision
par: Lin, Xin, et autres
Publié: (2025)

Motion Inversion for Video Customization
par: Wang, Luozhou, et autres
Publié: (2024)