Hugging Face's logo
Peng Liu's picture
2 5

Peng Liu

P3ngLiu
ruochenx's profile picture kyusonglee's profile picture tianchez's profile picture
·

AI & ML interests

CV, Multimodal, OVD

Recent Activity

liked a dataset 18 days ago
omlab/VLM-R1
reacted to tianchez's post with 🚀 21 days ago
Introducing VLM-R1! GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks? The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task). https://github.com/om-ai-lab/VLM-R1
reacted to tianchez's post with 👍 21 days ago
Introducing VLM-R1! GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks? The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task). https://github.com/om-ai-lab/VLM-R1
View all activity

Organizations

Om AI Lab's profile picture

P3ngLiu's activity

liked a dataset 18 days ago
reacted to tianchez's post with 🚀👍 21 days ago
view post
Post
4082
Introducing VLM-R1!

GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks?

The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task).

https://github.com/om-ai-lab/VLM-R1
·
liked a Space about 2 months ago
New activity in omlab/omdet-turbo-swin-tiny-hf 3 months ago

Image guided object detection

1
#3 opened 5 months ago by
godaspeg
updated a model 3 months ago
liked a model 4 months ago
liked a model 7 months ago
updated a model 9 months ago
New activity in omlab/OmDet-Turbo_tiny_SWIN_T 9 months ago

Update README.md

1
#1 opened 9 months ago by
nielsr
liked a model 12 months ago
updated a dataset about 1 year ago