Search Results for author:
Found 6 papers, 2 papers with code
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
We introduce SmolDocling, an ultra-compact vision-language model targeting end-to-end document conversion.
Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion
We introduce Docling, an easy-to-use, self-contained, MIT-licensed, open-source toolkit for document conversion, that can parse several types of popular document formats into a unified, richly structured representation.
Docling Technical Report
This technical report introduces Docling, an easy to use, self-contained, MIT-licensed open-source package for PDF document conversion.
Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs
We demonstrate the advantages of statements by applying our model to over 2700 tables from ESG reports.
Ranked #1 on
Information Extraction
on SemTabNet
Uncertainty Quantification for Rule-Based Models
Rule-based classification models described in the language of logic directly predict boolean values, rather than modeling a probability and translating it into a prediction as done in statistical models.
Differentiable Rule Induction with Learned Relational Features
On benchmark tasks, we show that these learned literals are simple enough to retain interpretability, yet improve prediction accuracy and provide sets of rules that are more concise compared to state-of-the-art rule induction algorithms.
