AI & ML interests
VLMs and long context, document processing and understanding, confidence, calibration, alignment, and decision making.
Recent Activity
Papers
GutenOCR: A Grounded Vision-Language Front-End for Documents
PubMed-OCR: PMC Open Access OCR Annotations
Organization Card
Data and models for optical character recognition
-
PubMed-OCR: PMC Open Access OCR Annotations
Paper • 2601.11425 • Published • 12 -
GutenOCR: A Grounded Vision-Language Front-End for Documents
Paper • 2601.14490 • Published • 37 -
rootsautomation/TABMEpp
Viewer • Updated • 122k • 104 • 5 -
rootsautomation/pubmed-ocr
Viewer • Updated • 1.55M • 1.45k • 70
Data and models for optical character recognition
-
PubMed-OCR: PMC Open Access OCR Annotations
Paper • 2601.11425 • Published • 12 -
GutenOCR: A Grounded Vision-Language Front-End for Documents
Paper • 2601.14490 • Published • 37 -
rootsautomation/TABMEpp
Viewer • Updated • 122k • 104 • 5 -
rootsautomation/pubmed-ocr
Viewer • Updated • 1.55M • 1.45k • 70
datasets 19
rootsautomation/MUSTARD
Viewer • Updated • 1.43k • 35
rootsautomation/MultiHiertt
Viewer • Updated • 8.87k • 32
rootsautomation/FinQA
Viewer • Updated • 8.28k • 37
rootsautomation/GloSAT
Preview • Updated • 41
rootsautomation/SciTSR-cc-by-nc-sa
Viewer • Updated • 889 • 42
rootsautomation/SciTSR-pd
Viewer • Updated • 108 • 40
rootsautomation/pubmed-ocr
Viewer • Updated • 1.55M • 1.45k • 70
rootsautomation/TABMEpp
Viewer • Updated • 122k • 104 • 5
rootsautomation/websrc-test
Viewer • Updated • 40.4k • 591
rootsautomation/websrc
Viewer • Updated • 360k • 1.16k • 7