Rui Zhao's picture

Rui Zhao

ruizhaocv

·

https://ruizhaocv.github.io/

AI & ML interests

Multimodal and GenAI

Recent Activity

upvoted a paper about 17 hours ago

Grounding Computer Use Agents on Human Demonstrations

upvoted a paper 8 days ago

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

authored a paper 9 days ago

UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback

View all activity

Organizations

Papers 10

arXiv:2511.01678

arXiv:2503.03651

arXiv:2410.07133

arXiv:2403.07420

spaces 1

MotionDirector

models 3

ruizhaocv/Edgen

Text-to-Image • Updated Oct 23, 2024 • 5

ruizhaocv/MotionDirector

Updated Dec 27, 2023 • 8

ruizhaocv/MotionDirector_weights

Updated Dec 13, 2023 • 4

datasets 0

None public yet