bytedance-research/Valley2-DPO
Updated
•
5
•
2
wuziheng
wuziheng
AI & ML interests
CV/SSL/MultiMedia
Recent Activity
updated
a model
2 days ago
bytedance-research/Valley2-DPO
published
a model
5 days ago
bytedance-research/Valley2-DPO
updated
a model
20 days ago
bytedance-research/Valley-Eagle-7B
Organizations
wuziheng's activity
updated
a
model
2 days ago
published
a
model
5 days ago
updated
a
model
20 days ago
reacted to
tianchez's
post with 🚀
about 2 months ago
Post
4312
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
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
- 3 replies
Update README.md
#3 opened 3 months ago
by
Hyggge
liked
a
model
4 months ago
liked
a
model
9 months ago
liked
a
model
about 1 year ago
liked
a
Space
over 1 year ago
authored
a
paper
over 1 year ago
authored
a
paper
almost 2 years ago
liked
a
model
almost 2 years ago
liked
a
Space
about 2 years ago