25 13 28

Xintao Wang

Xintao

https://xinntao.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 5 days ago

Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation

upvoted a paper 6 days ago

Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation

authored a paper 6 days ago

SketchVideo: Sketch-based Video Generation and Editing

View all activity

Organizations

Xintao's activity

authored a paper 5 days ago

Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation

Paper • 2503.24379 • Published 7 days ago • 68

upvoted a paper 6 days ago

Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation

Paper • 2503.24379 • Published 7 days ago • 68

authored a paper 6 days ago

SketchVideo: Sketch-based Video Generation and Editing

Paper • 2503.23284 • Published 9 days ago • 21

liked 2 datasets 7 days ago

KwaiVGI/MultiCamVideo-Dataset

Updated 5 days ago • 373 • 9

KwaiVGI/FullBench

Viewer • Updated 13 days ago • 1.4k • 758 • 2

upvoted a paper 7 days ago

FullDiT: Multi-Task Video Generative Foundation Model with Full Attention

Paper • 2503.19907 • Published 13 days ago • 8

authored a paper 13 days ago

Position: Interactive Generative Video as Next-Generation Game Engine

Paper • 2503.17359 • Published 17 days ago • 61

upvoted a paper 14 days ago

Position: Interactive Generative Video as Next-Generation Game Engine

Paper • 2503.17359 • Published 17 days ago • 61

authored a paper 17 days ago

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

Paper • 2503.14487 • Published 20 days ago • 27

upvoted a paper 19 days ago

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

Paper • 2503.14487 • Published 20 days ago • 27

authored a paper 21 days ago

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Paper • 2503.11647 • Published 24 days ago • 131

upvoted a paper 22 days ago

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Paper • 2503.11647 • Published 24 days ago • 131

authored a paper about 2 months ago

CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

Paper • 2502.08639 • Published Feb 12 • 43

upvoted a paper about 2 months ago

CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

Paper • 2502.08639 • Published Feb 12 • 43

liked a model about 2 months ago

KwaiVGI/VideoReward

Updated Feb 10 • 7

liked a dataset about 2 months ago

KwaiVGI/VideoGen-RewardBench

Viewer • Updated Feb 10 • 25.2k • 175 • 4

authored a paper 2 months ago

Improving Video Generation with Human Feedback

Paper • 2501.13918 • Published Jan 23 • 50

upvoted a paper 2 months ago

Improving Video Generation with Human Feedback

Paper • 2501.13918 • Published Jan 23 • 50

authored a paper 3 months ago

GameFactory: Creating New Games with Generative Interactive Videos

Paper • 2501.08325 • Published Jan 14 • 66

liked a model 3 months ago

KwaiVGI/3DTrajMaster

Updated Jan 22 • 4