UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-3B
Image-Text-to-Text
•
4B
•
Updated
•
4k
•
5
VLAA-Thinker
-
-
UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-7B
Image-Text-to-Text • 8B • Updated • 2.16k • 2 -
UCSC-VLAA/VLAA-Thinker-Qwen2VL-2B
Image-Text-to-Text • 2B • Updated • 135 • 1 -
UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B
Image-Text-to-Text • 8B • Updated • 10 -
UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B-Zero
Image-Text-to-Text • 8B • Updated • 12 -
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Paper • 2504.11468 • Published • 29