Yihao Feng
yihaocs
AI & ML interests
Deep Models.
Recent Activity
upvoted
a
paper
about 1 month ago
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid
Vision Tokenizer
liked
a dataset
6 months ago
nvidia/OpenMathReasoning
upvoted
a
paper
about 1 year ago
Law of Vision Representation in MLLMs
Organizations
