SicariusSicariiStuff/X-Ray_Alpha
Updated
•
308
•
56
popcat19
PopCat19
·
AI & ML interests
None yet
Recent Activity
liked
a model
12 days ago
SicariusSicariiStuff/X-Ray_Alpha
liked
a model
14 days ago
Sao10K/70B-L3.3-Cirrus-x1
upvoted
a
collection
16 days ago
Hamanasu
Organizations
None yet
PopCat19's activity
liked
a
model
12 days ago
liked
a
model
14 days ago
upvoted
a
collection
16 days ago
liked
11
models
16 days ago
PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
Text Generation
•
Updated
•
6.74k
•
104
bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF
Image-Text-to-Text
•
Updated
•
12.1k
•
16
mlabonne/gemma-3-27b-it-abliterated
Image-Text-to-Text
•
Updated
•
4.04k
•
121
Delta-Vector/Hamanasu-Magnum-QwQ-32B
Updated
•
270
•
7
mistralai/Mistral-Small-3.1-24B-Instruct-2503
Image-Text-to-Text
•
Updated
•
114k
•
1.05k
SicariusSicariiStuff/Oni_Mitsubishi_12B
Text2Text Generation
•
Updated
•
343
•
30
Gryphe/Pantheon-RP-1.8-24b-Small-3.1
Updated
•
529
•
42
bartowski/Gryphe_Pantheon-RP-1.8-24b-Small-3.1-GGUF
Text Generation
•
Updated
•
5.48k
•
9
RekaAI/reka-flash-3
Updated
•
5.14k
•
349
Delta-Vector/Hamanasu-QwQ-V2-RP
Updated
•
203
•
4
mradermacher/Hamanasu-QwQ-V2-RP-GGUF
Updated
•
541
•
2
liked
a
model
17 days ago
liked
a
model
27 days ago
liked
2
models
about 1 month ago
reacted to
tianchez's
post with 🚀👍
about 2 months ago
Post
4221
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