Xavier Theimer‑Lienhard

Xavier Theimer‑Lienhard

I am a Machine Learning Research Engineer at the LiGHT Lab (EPFL IC School and Harvard T.H. Chan School of Public Health) and a core contributor to Meditron, a medical LLM project.

I specialize in full‑stack medical LLMs, focusing on pre/post‑training, RLHF/DPO/GRPO, evaluation, and scalable inference. Recently, I have been working on Meditron-3 (8B/70B) and the Moove evaluation framework.

Previously, I was a Visiting Researcher at Yale University (BIDS). I hold an MSc in Data Science from EPFL.


News

Publications

Paper Figure
Llama-3-Meditron: An Open-Weight Suite of Medical LLMs Based on Llama-3.1
A. Sallinen, A.-J. Solergibert, M. Zhang, G. Boyé, M. Dupont-Roc, X. Theimer-Lienhard, E. Boisson, B. Bernath, H. Hadhri, A. Tran, T. Rabbani, T. Brokowski, Meditron Medical Doctor Working Group, T. G. J. Rudner, M.-A. Hartley
AAAI 2025 Workshop (GenAI4Health)
[PDF]
Paper Figure
GPoeT: a Language Model Trained for Rhyme Generation on Synthetic Data
A. Popescu-Belis, À. R. Atrio, B. Bernath, E. Boisson, T. Ferrari, X. Theimer-Lienhard, G. Vernikos
ACL SIGHUM 2023 (LaTeCH-CLfL)
[PDF]

Experience