Associate Professor
Aalborg University
Copenhagen, Denmark
Associate Prof. in ML at Aalborg Univ. CPH, working on probabilistic models, Bayesian learning theory & trustworthy AI. Open to collaborations and MSCA ideas.
I am an Associate Professor of Machine Learning at Aalborg University Copenhagen, working at the intersection of probabilistic modelling, Bayesian learning theory, deep learning, and trustworthy AI. My research focuses on building models that are both accurate and reliable by combining uncertainty quantification, probabilistic inference, and PAC-Bayesian methods. I have led and contributed to multiple international and Danish-funded projects—from spatio-temporal GeoAI to Bayesian deep learning.
I specialize in probabilistic machine learning, developing principled frameworks that enable machines to learn from data under uncertainty. I have authored 40 papers at major machine-learning conferences and 28 journal publications in top venues, primarily as first or lead author. My work has been recognized through competitive funding awards, including a highly selective Spanish starting grant (6% success rate) and a national research project. I also serve the community as Area Chair at AISTATS and as Area Editor for ACM Transactions on Probabilistic Machine Learning and Intelligent Data Analysis. In 2024, I organized an international summer school in probabilistic machine learning in Copenhagen, attracting more than 150 students from around the world.
Beyond research, I am strongly committed to high-quality teaching, PBL-driven education, and mentoring students as they transition into real-world AI practice.
Skills
Interests
Expertise
Expertise in probabilistic machine learning and uncertainty quantification for spatio-temporal forecasting and climate-aware modelling.
Expertise
Reliable Large Language Models Through Ensemble Methods and Wisdom-of-the-Crowds Principles
Expertise in designing reliable LLM systems via ensembles, uncertainty quantification, and wisdom-of-the-crowds principles.
Expertise
Probabilistic Machine Learning for Genome Recovery and Microbial Data
Probabilistic ML, deep generative models, and uncertainty-aware microbial genome recovery and large-scale metagenomics.
Expertise
Probabilistic Machine Learning and Generalization Theory in Modern Deep Learning
Probabilistic ML, PAC-Bayes/Chernoff theory, uncertainty, and generalization analysis for deep learning and over-parameterized models.