AI & ML interests
VLMs and long context, document processing and understanding, confidence, calibration, alignment, and decision making.
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 • 39 -
bevaya/TABMEpp
Viewer • Updated • 122k • 855 • 6 -
bevaya/pubmed-ocr
Viewer • Updated • 1.55M • 3.12k • 73
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 • 39 -
bevaya/TABMEpp
Viewer • Updated • 122k • 855 • 6 -
bevaya/pubmed-ocr
Viewer • Updated • 1.55M • 3.12k • 73
datasets 22
bevaya/ENTRANT
Viewer • Updated • 7.75M • 574
bevaya/CISOL
Viewer • Updated • 1.37k • 98
bevaya/HiTab-StatCan-NSF
Viewer • Updated • 8.71k • 351
bevaya/MUSTARD
Viewer • Updated • 1.43k • 14
bevaya/MultiHiertt
Viewer • Updated • 8.87k • 2.7k • 2
bevaya/FinQA
Viewer • Updated • 8.28k • 5.27k
bevaya/GloSAT
Viewer • Updated • 1k • 122
bevaya/SciTSR-cc-by-nc-sa
Viewer • Updated • 889 • 628
bevaya/SciTSR-pd
Viewer • Updated • 108 • 267
bevaya/pubmed-ocr
Viewer • Updated • 1.55M • 3.12k • 73