Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
Paper
•
2505.03318
•
Published
•
92
kj
Xiakj
·
AI & ML interests
None yet
Recent Activity
new activity
2 days ago
lightonai/LightOnOCR-2-1B:"model_type": "lighton_ocr"
new activity
2 days ago
lightonai/LightOnOCR-2-1B:Testing OCR using vllm returns nothing but exclamation marks.
upvoted
a
paper
9 months ago
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement
Fine-Tuning
Organizations
None yet
"model_type": "lighton_ocr"
6
#7 opened 3 days ago
by
KoichiYasuoka
Testing OCR using vllm returns nothing but exclamation marks.
10
#1 opened 4 days ago
by
rsbdev
upvoted
a
paper
9 months ago
liked
a
model
11 months ago
