Yuqi Wang

Greenbean's activity

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

liked a dataset 1 day ago

AI-MO/NuminaMath-1.5

Viewer • Updated 1 day ago • 896k • 146 • 65

New activity in MMInstruction/ArxivCap 8 days ago

Missing sub_caption

2

#6 opened 9 days ago by

andreamad8

liked a dataset 27 days ago

PleIAs/YouTube-Commons

Updated Jun 26, 2024 • 893 • 336

liked a model 28 days ago

MiniMaxAI/MiniMax-VL-01

Image-Text-to-Text • Updated 18 days ago • 2.31k • 234

New activity in MMInstruction/ArxivQA 30 days ago

Arxiv IDs in the Dataset

1

#3 opened about 1 month ago by

ghazalkhn

liked a model about 2 months ago

openai/whisper-small

Automatic Speech Recognition • Updated Feb 29, 2024 • 12.3M • 350

liked a model 2 months ago

openai/whisper-large-v3

Automatic Speech Recognition • Updated Aug 12, 2024 • 4.02M • • 4.02k

liked 2 datasets 2 months ago

LIUM/tedlium

Updated Sep 10, 2024 • 1.15k • 25

amphion/Emilia-Dataset

Viewer • Updated Sep 6, 2024 • 52.9M • 32.5k • 211

liked a model 2 months ago

Qwen/Qwen2-VL-72B-Instruct

Image-Text-to-Text • Updated 6 days ago • 122k • 275

liked a model 3 months ago

Qwen/Qwen2-72B-Instruct

Text Generation • Updated Oct 8, 2024 • 48.5k • • 703

liked a dataset 3 months ago

5CD-AI/Viet-Doc-VQA

Viewer • Updated Aug 25, 2024 • 51.9k • 111 • 64

liked a dataset 4 months ago

neulab/PangeaInstruct

Updated 9 days ago • 803 • 81

updated a dataset 4 months ago

MMInstruction/ArxivCap

Viewer • Updated Oct 3, 2024 • 573k • 3.72k • 50

liked a dataset 4 months ago

CarperAI/pilev2-dev

Preview • Updated Mar 13, 2023 • 53 • 24

liked 3 datasets 5 months ago

m-a-p/PIN-14M

Viewer • Updated Dec 20, 2024 • 68.1k • 10.9k • 28

wikimedia/structured-wikipedia

Preview • Updated Nov 14, 2024 • 750 • 58

Mutonix/Vript

Viewer • Updated Jun 11, 2024 • 409k • 10.8k • 18

reacted to maxiw's post with 👀 5 months ago

view post

Post

2893

The new Qwen-2 VL models seem to perform quite well in object detection. You can prompt them to respond with bounding boxes in a reference frame of 1k x 1k pixels and scale those boxes to the original image size.

You can try it out with my space maxiw/Qwen2-VL-Detection

• 

• 
• 
• 
• 4 replies

·

👍

11

11

👀

5

5

🤗

1

1

+

Reply

liked a dataset 5 months ago

Zhihui/VLFeedback

Viewer • Updated Sep 3, 2024 • 382k • 271 • 8