Kamyar Zeinalipour GitHub Hugging Face

Language models for Europe's languages, and for the ones with almost no data at all.

Also in classrooms, protein design and gas turbines.

Kamyar Zeinalipour, postdoctoral researcher at the University of Siena and AI engineer at Villanova.AI.

See the researchPublications

Thirty-one papers and the nine languages they work in. Point at a dot to see what it is, drag it and let it go, or click a language to keep its links lit; click anywhere else to see everything again.

Latest

  1. 11 November 2026

    Villanova.AI released Villanova2: a dense 2.4B and a 15.5B mixture of experts for Europe's languages, with open weights and documented open data. All four models cite Multi-SFT, our paper on permissively licensed multilingual instruction data.

    In the publications The models

  2. November 2026

    Tildea opened in early access: paste a job posting and it writes a resume for it from what you have really done, and leaves out anything you have not.

    tildea.ai

  3. November 2026

    Finished publishing seventeen research releases: every paper with code now has one repository and one model collection, cross-linked.

    All seventeen releases

All updates

Recent papers

All thirty-one papers