Hugging Face's logo
Xiangtai Li's picture
12 16 13

Xiangtai Li

LXT
malikzeeshan's profile picture BryanW's profile picture yehors-cv's profile picture
·
https://lxtgh.github.io/

AI & ML interests

Computer Vision, Multi-Modal Understanding, Generative AI

Recent Activity

reacted to merve's post with 👍 1 day ago
ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license 💗 https://huggingface.co/collections/ByteDance/sa2va-model-zoo-677e3084d71b5f108d00e093 > The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) both for images and videos ⏯️ > The models come in 1B, 4B and 8B and are based on InternVL2.5 for base architecture and Qwen2, Qwen2.5 and InternLM2 for language model part (depending on the checkpoint) > The model is very interesting, it has different encoders for different modalities each (visual prompt, text prompt, image and video) then it concatenates these to feed into LLM 💬 the output segmentation tokens are passed to SAM2, to sort of match text (captions or semantic classes) to masks ⤵️ > Their annotation pipeline is also interesting, they seems to use two open large vision LMs to refine the annotations, and have different levels of descriptions to provide consistency.
reacted to merve's post with 🔥 1 day ago
ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license 💗 https://huggingface.co/collections/ByteDance/sa2va-model-zoo-677e3084d71b5f108d00e093 > The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) both for images and videos ⏯️ > The models come in 1B, 4B and 8B and are based on InternVL2.5 for base architecture and Qwen2, Qwen2.5 and InternLM2 for language model part (depending on the checkpoint) > The model is very interesting, it has different encoders for different modalities each (visual prompt, text prompt, image and video) then it concatenates these to feed into LLM 💬 the output segmentation tokens are passed to SAM2, to sort of match text (captions or semantic classes) to masks ⤵️ > Their annotation pipeline is also interesting, they seems to use two open large vision LMs to refine the annotations, and have different levels of descriptions to provide consistency.
authored a paper 2 days ago
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
View all activity

Organizations

ZeroGPU Explorers's profile picture Dense World's profile picture MeissonFlow Research's profile picture

LXT's activity

liked a model 3 days ago
liked a dataset 22 days ago
liked a dataset about 1 month ago
liked a model 2 months ago
liked a Space 3 months ago
liked a model 3 months ago
liked 2 models 6 months ago
liked a Space 6 months ago
liked a model 7 months ago
liked a dataset 9 months ago
liked a Space 12 months ago
liked a model 12 months ago