Cédric Caruzzo

Cédric Caruzzo

AI Research Scientist at Lunit Inc.

Vision Foundation Models · LLM Post-Training · Medical AI

About Me

I'm an AI Research Scientist at Lunit working on foundation models and post-training for medical AI.

I'm interested in how learned systems behave under change: how they adapt, generalize, forget, exploit objectives, and fail when deployed beyond their training distribution. My work spans representation learning, post-training, evaluation, and increasingly agentic systems, with a focus on understanding and improving model reliability.

Previously, I worked on pathology foundation models at Lunit, Cell Painting foundation models at KAIST, and computer vision for drug discovery at Institut Pasteur.

Publications

arXiv ’26
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
Cédric Caruzzo, Donggeun Yoo, Tae Soo Kim
arXiv preprint arXiv:2607.09349, 2026
arXiv ’25
CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis
Cédric Caruzzo, Jong Chul Ye
arXiv preprint arXiv:2509.06986, 2025
SLAS Europe ’24 Poster
Cellular Phenotypic Profiling: Combining Live Imaging & Cell Painting Techniques
Soonju Park, Cédric Caruzzo, Nakyung Lee,
Poster presented at SLAS Europe 2024, Barcelona, Spain, 2024
Sci Reports ’21
Wolbachia detection in Aedes aegypti using MALDI-TOF MS coupled to artificial intelligence
Antsa Rakotonirina, Cédric Caruzzo, Valentine Ballan,
Scientific Reports 11, 21355, 2021