QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
Paper
•
2502.05178
•
Published
•
10
•
2
Yue Zhao
zhaoyue-zephyrus
AI & ML interests
None yet
Recent Activity
liked
a model
about 14 hours ago
nvidia/QLIP-L-14-392
liked
a model
about 14 hours ago
nvidia/QLIP-B-8-256
liked
a model
about 14 hours ago
nvidia/QLIP-B-16-256
Organizations
None yet
zhaoyue-zephyrus's activity
commented
a
paper
5 days ago