LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
Paper
β’
2509.23661
β’
Published
β’
44
~
QuadLiFrain
Β·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal
Training
updated
a collection
5 months ago
CV
liked
a Space
5 months ago
omlab/VLM-R1-Referral-Expression
Organizations
None yet
upvoted
a
paper
about 1 month ago