MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Paper
•
2509.16197
•
Published
•
52
Bowen Pan
bpan
AI & ML interests
Efficient LLM, Mixture-of-Experts, Embodied AI, Dynamic Neural Network
Recent Activity
upvoted
a
paper
about 1 month ago
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid
Vision Tokenizer
authored
a paper
about 1 month ago
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid
Vision Tokenizer
upvoted
an
article
over 1 year ago
How NuminaMath Won the 1st AIMO Progress Prize
Organizations
authored
a
paper
about 1 month ago
authored
a
paper
about 2 years ago