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 • 38 -
bevaya/TABMEpp
Viewer • Updated • 122k • 466 • 5 -
bevaya/pubmed-ocr
Viewer • Updated • 1.55M • 2.23k • 71
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 • 38 -
bevaya/TABMEpp
Viewer • Updated • 122k • 466 • 5 -
bevaya/pubmed-ocr
Viewer • Updated • 1.55M • 2.23k • 71
datasets 22
bevaya/ENTRANT
Viewer • Updated • 7.75M • 1.73k
bevaya/CISOL
Viewer • Updated • 1.37k • 56
bevaya/HiTab-StatCan-NSF
Viewer • Updated • 8.71k • 82
bevaya/MUSTARD
Viewer • Updated • 1.43k • 56
bevaya/MultiHiertt
Viewer • Updated • 8.87k • 72
bevaya/FinQA
Viewer • Updated • 8.28k • 295
bevaya/GloSAT
Viewer • Updated • 1k • 60
bevaya/SciTSR-cc-by-nc-sa
Viewer • Updated • 889 • 55
bevaya/SciTSR-pd
Viewer • Updated • 108 • 52
bevaya/pubmed-ocr
Viewer • Updated • 1.55M • 2.23k • 71