Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Paper
•
2501.04001
•
Published
•
34
Shilin Xu
shilinxu
AI & ML interests
None yet
Recent Activity
updated
a dataset
2 days ago
shilinxu/RLAIF-V-Dataset
new activity
2 days ago
shilinxu/Qwen2VL-7B-ViT:Want to access the model
authored
a paper
2 days ago
LLAVADI: What Matters For Multimodal Large Language Models Distillation
Organizations
