Unicorn: Text-Only Data Synthesis for Vision Language Model Training
Paper
•
2503.22655
•
Published
•
37
Yu_xm
Yu2020
AI & ML interests
None yet
Recent Activity
authored
a paper
7 days ago
Unicorn: Text-Only Data Synthesis for Vision Language Model Training
upvoted
a
paper
7 days ago
Unicorn: Text-Only Data Synthesis for Vision Language Model Training
Organizations
Yu2020's activity
authored
2
papers
7 days ago
upvoted
a
paper
7 days ago
upvoted
a
paper
about 1 month ago
commented on
SigLIP 2: A better multilingual vision language encoder
about 2 months 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
about 2 months 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
about 2 months ago
updated
a
dataset
about 2 months ago
published
a
dataset
about 2 months ago
published
a
model
2 months ago
Version Issue
2
#1 opened over 1 year ago
by
Yu2020