From Pixels to Words -- Towards Native One-Vision Models at Scale
Haiwen Diao
Paranioar
AI & ML interests
Vision-and-Language, Parameter-efficient Transfer Learning, Multi-modal Large Language Model
Recent Activity
upvoted a paper 1 day ago
dNaViT: Discrete Codes are General-Purpose Visual Representations authored a paper 7 days ago
From Pixels to Actions - Towards Native Vision-Language-Action Policies authored a paper 7 days ago
Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative TransformersOrganizations
