LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
Paper • 2509.23661 • Published • 51
Georgios Skyrianos
geoskyr
AI & ML interests
Image/Data processing , computer vision
Recent Activity
new activity about 20 hours ago
lmarena-ai/arena-expert-5k:Safe conversation parsing updated a dataset 1 day ago
geoskyr/arena-expert-UPE published a dataset 1 day ago
geoskyr/arena-expert-UPEOrganizations
upvoted a paper 16 days ago