popcat19

PopCat19

PopCat19

AI & ML interests

None yet

Recent Activity

liked a model about 1 month ago

SicariusSicariiStuff/X-Ray_Alpha

liked a model about 1 month ago

Sao10K/70B-L3.3-Cirrus-x1

upvoted a collection about 1 month ago

Hamanasu

View all activity

Organizations

None yet

PopCat19's activity

liked 2 models about 1 month ago

SicariusSicariiStuff/X-Ray_Alpha

Updated 24 days ago • 382 • 60

Sao10K/70B-L3.3-Cirrus-x1

Text Generation • Updated Jan 7 • 103k • 29

upvoted a collection about 1 month ago

Hamanasu

Collection

A brand new series of Models from yours truly, Designed for Intelligence, Creativity and Roleplay - R/Locallama keeps DELETING MY GODDAMN COMMENTS • 31 items • Updated 16 days ago • 8

liked 12 models about 1 month ago

liked 3 models about 2 months ago

TheDrummer/Cydonia-24B-v2.1

Updated Mar 7 • 582 • 40

Delta-Vector/Archaeo-12B-GGUF

Text Generation • Updated Feb 23 • 1.09k • 11

Delta-Vector/Archaeo-12B

Text Generation • Updated Feb 28 • 118 • 12

reacted to tianchez's post with 🚀👍 2 months ago

Post

4324

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

3 replies