chongyi
yuzaa
AI & ML interests
multimodal large language models
Recent Activity
authored a paper about 16 hours ago
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs? updated a model 1 day ago
openbmb/MiniCPM-V-4.6 updated a collection 1 day ago
MiniCPM-V