QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
Paper
•
2502.05178
•
Published
•
10
Shuhan Tan
tanshh97
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive
Multimodal Understanding and Generation
authored
a paper
8 months ago
Wolf: Captioning Everything with a World Summarization Framework
upvoted
a
paper
over 1 year ago
Language Conditioned Traffic Generation
Organizations
None yet