2 1

Yu_xm

Yu2020

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing

commented on an article 5 days ago

SigLIP 2: A better multilingual vision language encoder

commented on an article 6 days ago

SigLIP 2: A better multilingual vision language encoder

View all activity

Organizations

Yu2020's activity

upvoted a paper 3 days ago

VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing

Paper • 2502.17258 • Published 4 days ago • 58

commented on SigLIP 2: A better multilingual vision language encoder 5 days ago

This is related to one of my papers. If you are interested, we can discuss the details via email. 😄

commented on SigLIP 2: A better multilingual vision language encoder 6 days ago

"When using the standalone GemmaTokenizerFast make sure to pass padding="max_length" and max_length=64 as that’s how the model was trained." Does Siglip2 support longer text input? If the max_length is set to 256 or 512, will text exceeding 64 be truncated?

commented a paper 6 days ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 8 days ago • 118 •

updated a dataset 11 days ago

Yu2020/office

Preview • Updated 11 days ago • 10

published a dataset 11 days ago

Yu2020/office

Preview • Updated 11 days ago • 10

published a model about 1 month ago

Yu2020/Unicorn

Updated Jan 27

New activity in yuanzhoulvpi/vit-gpt2-image-chinese-captioning over 1 year ago

Version Issue

#1 opened over 1 year ago by

Yu2020