MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Paper • 2509.16197 • Published • 58
Bowen Pan
bpan
AI & ML interests
Efficient LLM, Mixture-of-Experts, Embodied AI, Dynamic Neural Network
Organizations
upvoted a paper 6 months ago
upvoted an article over 1 year ago
Article
How NuminaMath Won the 1st AIMO Progress Prize
- +6
•
128
upvoted a collection almost 2 years ago
upvoted 2
articles almost 2 years ago
Article
Saving Memory Using Padding-Free Transformer Layers during Finetuning
•
21
Article
DS-MoE: Making MoE Models More Efficient and Less Memory-Intensive
•
30