MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Paper
•
2509.16197
•
Published
•
54
Haoshuo Huang
haosoul122
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid
Vision Tokenizer
upvoted
a
paper
about 1 month ago
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid
Vision Tokenizer
Organizations
None yet
authored
a
paper
about 1 month ago