Multimodal OCR: Parse Anything from Documents
Paper
• 2603.13032 • Published
• 23
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
CodePercept: Code-Grounded Visual STEM Perception for MLLMs
From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
Add ScreenSpot-Pro evaluation result (Qwen2.5-VL-7B-Instruct)
#67 opened about 7 hours ago
by
merve
Add ScreenSpot-Pro evaluation result (Qwen2.5-VL-72B-Instruct)
#34 opened about 7 hours ago
by
merve
Add ScreenSpot-Pro evaluation result (Qwen2.5-VL-3B-Instruct)
#48 opened about 7 hours ago
by
merve
Add ScreenSpot-Pro evaluation result (Qwen2.5-VL-32B-Instruct)
#22 opened about 7 hours ago
by
merve
Add ScreenSpot-Pro evaluation result (Qwen2-VL-7B)
#87 opened about 7 hours ago
by
merve
Add ScreenSpot-Pro evaluation result (Qwen2-VL-72B-Instruct)
#11 opened about 7 hours ago
by
merve
Add ScreenSpot-Pro evaluation result (Qwen-VL-7B)
#14 opened about 7 hours ago
by
merve
akhaliq
submitted a paper to Daily Papers 2 days ago
Update medical vqa score
#65 opened 3 days ago
by
StevenTang
clefourrier
authored a paper 5 days ago
AdinaY
submitted a paper to Daily Papers 5 days ago
xianbao
submitted a paper to Daily Papers 5 days ago
TongkunGuan
submitted a paper to Daily Papers 6 days ago
Antimage01
submitted a paper to Daily Papers 8 days ago
AdinaY
submitted a paper to Daily Papers 9 days ago
ksshumab
submitted a paper to Daily Papers 14 days ago
littlebird13
published 4 models 14 days ago
Qwen/Qwen3.5-397B-A17B-GPTQ-Int4
Image-Text-to-Text • Updated
• 14.8k • 17
Qwen/Qwen3.5-122B-A10B-GPTQ-Int4
Image-Text-to-Text • 125B • Updated
• 96k • 28
Qwen/Qwen3.5-27B-GPTQ-Int4
Image-Text-to-Text • 28B • Updated
• 161k • 26
Qwen/Qwen3.5-35B-A3B-GPTQ-Int4
Image-Text-to-Text • 36B • Updated
• 283k • 47