1 6

wuziheng

wuziheng

AI & ML interests

CV/SSL/MultiMedia

Recent Activity

updated a model 4 days ago

bytedance-research/Valley-Eagle-7B

reacted to tianchez's post with 🚀 22 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

new activity about 2 months ago

bytedance-research/Valley-Eagle-7B:Update README.md

View all activity

Organizations

wuziheng's activity

updated a model 4 days ago

bytedance-research/Valley-Eagle-7B

Updated 4 days ago • 517 • 32

reacted to tianchez's post with 🚀 22 days ago

Post

4122

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