About

I’m a tenured research scientist at the RIKEN Center for Advanced Intelligence Project, affiliated with the Approximate Bayesian Inference team and a core member of the Bayes Duality project. Before that, I was a postdoctoral researcher working with Emtiyaz Khan. I completed my PhD in the Computer Vision Group at TU Munich under the guidance of Daniel Cremers.

My current research focuses on the design and analysis of new algorithms to improve deep learning via Bayesian principles, with the aim to develop methods that are robust, adaptable and more interpretable.

News

• Feb 29, 2024. New preprint. We show that large models like GPT-2 can be successfully trained and improved using variational learning
• Jan 17, 2024. Two papers are accepted at ICLR 2024: [Model Merging by Uncertainty-Based Gradient Matching] and [Conformal Prediction via Regression-as-Classification].
• Dec 9, 2023. Heading off to the NeurIPS conference, see you there!
• Dec 8, 2023. Invited talk at the Georgia Tech Applied and Computational Mathematics Seminar.
• Oct 20, 2023. One new preprint [Model Merging by Uncertainty-Based Gradient Matching] available!
• Sep 22, 2023. One paper accepted at NeurIPS 2023. See you in New Orleans in December!
• Sep 14, 2023. I gave an invited talk at the JST CREST Yoshida Khan Workshop, University of Tokyo.
• Aug 24, 2023. I will serve as an area chair for AISTATS ‘24 and ICLR ‘24.
• Aug 1, 2023. The ICML 2023 workshop on duality principles was a success! Here are the slides of all talks.
• Jul 22 - 29, 2023. I’ll be attending ICML in Hawaii, reach out if you want to catch up or have a chat!
• May 25, 2023. I gave two invited lectures on Bayesian deep learning at UNIST AIGS (Ulsan, Korea) and at SungKyunKwan University (Seoul, Korea).

See older news.