juyi

juyil

·

AI & ML interests

None yet

Recent Activity

new activity 6 days ago

nvidia/MMOU:`video_duration` is minutes×60 for two rows in MMOU_TEST_MINI.json

new activity 12 days ago

NU-World-Model-Embodied-AI/phyground:[bot] Conversion to Parquet

new activity 12 days ago

NU-World-Model-Embodied-AI/phyground:Kandinsky-WM in PhyGround

View all activity

Organizations

upvoted a paper 3 months ago

PhyGround: Benchmarking Physical Reasoning in Generative World Models

Paper • 2605.10806 • Published May 11 • 3

upvoted a paper 6 months ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 527

upvoted a collection about 1 year ago

Vote Vision-language-action Model

Code: https://github.com/LukeLIN-web/vote 8act means the action chunk size is 8; it generates 8 actions in a single inference. • 4 items • Updated Mar 2 • 1