FETA: Towards Specializing Foundational Models for Expert Task ApplicationsAmit AlfassyAssaf Arbelleet al.2022NeurIPS 2022
Delivering Document Conversion as a Cloud Service with High Throughput and ResponsivenessChristoph AuerMichele Dolfiet al.2022CLOUD 2022
ESG Accountability Made Easy: DocQA at Your ServiceLokesh MishraCesar Berrospi Ramiset al.2024AAAI 2024
Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIsLokesh MishraSohayl Dhibiet al.2024ACL 2024
Docling: An Efficient Open-Source Toolkit for AI-driven Document ConversionNikos LivathinosChristoph Aueret al.2025AAAI 2025
INDUS: Effective and Efficient Language Models for Scientific ApplicationsBhatta BhattacharjeeAashka Trivediet al.2024EMNLP 2024
DocLayNet: A Large Human-Annotated Dataset for Document-Layout SegmentationBirgit PfitzmannChristoph Aueret al.2022KDD 2022
Corpus conversion service: A machine learning platform to ingest documents at scalePeter StaarM. Dolfiet al.2018KDD 2018
Robust PDF Document Conversion Using Recurrent Neural NetworksNikolaos LivathinosCesar Berrospiet al.2021IAAI 2021