LLaVA-NeXT
Collection
Some powerful image models.
•
10 items
•
Updated
•
5
Daniel Lima
danielfl
·
AI & ML interests
Newbie in AI trying to learn by doing. I am also creating a highly skilled free chatbot.
Recent Activity
upvoted
a
collection
18 days ago
LLaVA-NeXT
liked
a model
about 2 months ago
bartowski/simplescaling_s1-32B-GGUF
Organizations
None yet
danielfl's activity
upvoted
a
collection
18 days ago
liked
a
model
about 2 months ago
reacted to
tianchez's
post with 🚀
about 2 months ago
Post
4229
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
liked
a
model
over 1 year ago
liked
a
Space
over 1 year ago
