1 3 6

Kevin

kvnptl

kvnptl

AI & ML interests

Robot perception

Recent Activity

upvoted an article 3 days ago

SmolVLM - small yet mighty Vision Language Model

reacted to maxiw's post with 👍 13 days ago

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 https://huggingface.co/spaces/maxiw/Qwen2-VL-Detection

upvoted an article about 1 month ago

Welcome PaliGemma 2 – New vision language models by Google

View all activity

Organizations

None yet

kvnptl's activity

upvoted an article 3 days ago

Article

SmolVLM - small yet mighty Vision Language Model

Nov 26, 2024

• 220

reacted to maxiw's post with 👍 13 days ago

Post

3111

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