Skip to content

Source paper

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Ahmed Nassar, Andres Marafioti, Matteo Omenetti and 10 more

Ahmed Nassar, Andres Marafioti, Matteo Omenetti, Maksym Lysak, Nikolaos Livathinos, Christoph Auer, Lucas Morin, Rafael Teixeira de Lima, Yusik Kim, A. Said Gurbuz, Michele Dolfi, Miquel Farré, Peter W. J. Staar

arXiv 2503.11576 · 2025120 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

SmolDocling is a 256M parameter vision-language model designed for efficient, end-to-end document conversion, mapping page images directly to a structured 'DocTags' markup format. It significantly reduces computational overhead compared to larger models while maintaining robust performance across diverse document elements like tables, charts, and equations.

How it works (AI summary)

The model utilizes a SigLIP vision encoder with pixel-shuffle compression and a 135M parameter SmolLM-2 language backbone to autoregressively generate a unified XML-like representation that captures content, spatial location, and hierarchical document structure in a single pass.