Bin Xiao's picture

Bin Xiao

leoxiaobin

·

https://leoxiaobin.github.io/

leoxiaobin

AI & ML interests

Large-scale Foundation Model Training; Computer Vision; Deep Learning

Recent Activity

new activity about 7 hours ago

microsoft/Florence-2-base:add confidence scores for `od` and `description_with_bboxes` tasks

new activity about 8 hours ago

microsoft/Florence-2-base:Fix invalid escape sequences

new activity about 8 hours ago

microsoft/Florence-2-base:Fix the error "only DaViT is supported for now" appears whenloading the fine-tuned model

View all activity

Organizations

liked a model 12 months ago

microsoft/Phi-3.5-vision-instruct

Image-Text-to-Text • 4B • Updated Sep 26, 2024 • 802k • 701

liked a Space 12 months ago

Florence2 + SAM2

Segment objects in images and videos using text prompts

liked 4 Spaces about 1 year ago

Better Florence 2

Interact with Florence-2 to analyze images and generate descriptions

Florence2 WebGPU

Generate realistic images from textual descriptions

Florence 2

Florence 2

Analyze images to generate captions, detect objects, or perform OCR

liked 7 models about 1 year ago

microsoft/Florence-2-base-ft

Image-Text-to-Text • 0.2B • Updated about 8 hours ago • 23.8k • 124

microsoft/Florence-2-large

Image-Text-to-Text • 0.8B • Updated about 8 hours ago • 1.11M • 1.62k

microsoft/Florence-2-base

Image-Text-to-Text • 0.2B • Updated about 7 hours ago • 522k • 286

microsoft/Florence-2-large-ft

Image-Text-to-Text • 0.8B • Updated about 8 hours ago • 21.7k • 360

microsoft/Phi-3-vision-128k-instruct-onnx-cuda

Text Generation • Updated Nov 14, 2024 • 16 • 27

microsoft/Phi-3-vision-128k-instruct

Text Generation • 4B • Updated Aug 20, 2024 • 24.2k • 963

microsoft/Phi-3-mini-128k-instruct

Text Generation • 4B • Updated Mar 2 • 1.06M • 1.66k