Haiping Wu

haipingwu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored a paper 24 days ago

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

Paper • 2412.04424 • Published 25 days ago • 57

New activity in microsoft/Florence-2-large about 1 month ago

initial tuned 4k context length model

4

#84 opened about 1 month ago by

haipingwu

Has there been some breaking changes ?

2

#81 opened about 2 months ago by

skylord

Trying to get bounding box confidence values for object detection

4

#55 opened 5 months ago by

AHuaw

updated a model about 1 month ago

microsoft/Florence-2-large

Image-Text-to-Text • Updated 22 days ago • 382k • 1.32k

New activity in microsoft/Florence-2-large about 2 months ago

add_confidence_score

1

#56 opened 5 months ago by

haipingwu

Image classification

1

#79 opened 2 months ago by

mvukic

New activity in microsoft/Florence-2-base about 2 months ago

Inherit from GenerationMixin

#22 opened about 2 months ago by

fcakyon

New activity in microsoft/Florence-2-large about 2 months ago

Inherit from GenerationMixin

3

#80 opened 2 months ago by

Link161

New activity in microsoft/Phi-3.5-vision-instruct 3 months ago

Generating multiple images

1

#18 opened 4 months ago by

Barshan

Unexpected behavior of Phi-3.5-vision model with respect to 4K token length.

1

#14 opened 4 months ago by

ita9naiwa

fix_rope_scaling

#28 opened 3 months ago by

haipingwu

updated a model 3 months ago

microsoft/Phi-3.5-vision-instruct

Image-Text-to-Text • Updated Sep 26 • 264k • 626

New activity in microsoft/Phi-3.5-vision-instruct 4 months ago

Add proper library name

#23 opened 4 months ago by

osanseviero

Fix task tag

#16 opened 4 months ago by

merve

total images must be the same as the number of image tags

1

#12 opened 4 months ago by

wvangils

is it possible to replace my image processor 'openai/clip-vit-large-patch14-336'?

1

#13 opened 4 months ago by

hmhanna

New activity in microsoft/Florence-2-large 4 months ago

Pretrained model's performance is bad on vqa tasks

1

#63 opened 5 months ago by

hcy511

New activity in microsoft/Phi-3.5-vision-instruct 4 months ago

Fix spelling error in README

1

#10 opened 4 months ago by

fromplutowithlove

`TypeError` When Processing Text and Image Batch with `processor`

3

#5 opened 4 months ago by

Mohammadreza