Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
Paper • 2412.04424 • Published • 62 •
4
Alberto Baldrati
ABaldrati
AI & ML interests
None yet
Recent Activity
authored a paper 21 days ago
VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions authored a paper 3 months ago
More Images, More Problems? A Controlled Analysis of VLM Failure ModesOrganizations
commented 2
papers over 1 year ago