Celia Cintas
Computer Scientist
My name is Celia Cintas (🇦🇷), I’m a Staff Research Scientist at IBM Research Africa – Nairobi. I’m a member of the AI Science team at the Kenya Lab.
Photo by German Garcia Andrasti
Lastest news
Localizing Persona Representations in LLMs
Introduction Understanding the mechanisms by which large language models (LLMs) process information, store knowledge, and generate outputs...
Spatially Constrained Search in Optical Flow Networks
Introduction With the emergence of deep learning techniques and the availability of large-scale datasets, optical flow estimation performance has...
Talks
-
Español
2da Escuela de Primavera en Deep Learning
Invited Lecture: Exploración y análisis de representaciones internas en redes neuronales -
English
6th Big Data Africa School
Invited Lecture: Introduction to Machine Learning
-
English
The Science Forum South Africa 2025
Showcasing UK-SA Innovation & Entrepreneurship Strengthening Models
Latest publications
-
arXiv preprint
Puech, A., Mazzonelli, M., Govindasamy, T.R., Mngomezulu, M., Maeso-GarcÃa, H., Tolhurst, T., Bayazi, J., Moeini, A., Simumba, N., Cintas, C. and Nelischer, D., 2026. GENCO-A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis.
-
arXiv preprint
Puech, A., Mazzonelli, M., Cintas, C., Govindasamy, T.R., Mngomezulu, M., Weiss, J., Baù, M., Varbella, A., Mirallès, F., Kim, K. and Xie, L., 2025. gridfm-datakit-v1: A Python Library for Scalable and Realistic Power Flow and Optimal Power Flow Data Generation.
Comms
-
English
From vision to reality: a unified neural solver for the power grid
-
English
When AI models begin to notice their own thoughts
