Georgios Batzolis
PhD student at the University of Cambridge
I am currently a 4th year PhD student at the Department of Applied Mathematics and Theoretical Physics (DAMTP) at the University of Cambridge, under the supervision of Prof. Carola-Bibiane Schönlieb. My research focuses on generative modeling, with a particular emphasis on diffusion models.
Recently, I have become deeply interested in disentangled representation learning and the extraction of data manifold properties from pretrained generative models, including diffusion models and normalizing flows. Additionally, I have been exploring the fascinating area of Schrödinger Bridges.
Education
University of Cambridge
(Oct 2020 - present)
Department of Applied Mathematics
PhD in Generative AI
PhD in Generative AI
University of Cambridge
(Oct 2016 - Oct 2020)
Department of Engineering
MEng in Information and Computer Engineering, First Class Honours
MEng in Information and Computer Engineering, First Class Honours
Research Visits
University of Oxford
(Oct 2023 - Jan 2024)
Department of Statistics
Visited Doucet-Deligiannidis (D^2) group
Visited Doucet-Deligiannidis (D^2) group
Work Experience
Google DeepMind
Research Collaboration (Feb 2024 - present)
Huawei Technologies Research & Development (UK) Ltd
AI Research Internship (July 2022 - Oct 2022)
MediaTek Research UK Ltd
AI Research Internship (June 2020 - Oct 2020)
Publications
ICML 2024
Your diffusion model secretly knows the dimension of the data manifold, Jan Stanczuk*, Georgios Batzolis*, Teo Deveney, Carola-Bibiane Schönlieb, ICML 2024
[Published Version] [arXiv] [Official Code] [Demo/Clean Code] [Official Webpage]
[Published Version] [arXiv] [Official Code] [Demo/Clean Code] [Official Webpage]
FoDS
CAFLOW: conditional autoregressive flows, Georgios Batzolis, Marcello Carioni, Christian Etmann, Soroosh Afyouni, Zoe Kourtzi, Carola-Bibiane Schönlieb, Foundations of Data Science, AIMS, 2024
Doi: 10.3934/fods.2024028
[Published Version] [arXiv] [Official Code]
Doi: 10.3934/fods.2024028
[Published Version] [arXiv] [Official Code]
AAAI 2022
How to distribute data across tasks for meta-learning?, Alexandru Cioba, Michael Bromberg, Qian Wang, Ritwik Niyogi, Georgios Batzolis, Jezabel Garcia, Da-shan Shiu, Alberto Bernacchia, Proceedings of the AAAI Conference on Artificial Intelligence, 2022
[PDF]
[PDF]
arXiv
Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models, Georgios Batzolis*, Jan Stanczuk*, Carola-Bibiane Schönlieb, arXiv preprint arXiv:2304.12141, 2023
[PDF]
[PDF]
Non-uniform diffusion models, Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb, arXiv preprint arXiv:2207.09786, 2022
[PDF]
[PDF]
Conditional image generation with score-based diffusion models, Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb, Christian Etmann, arXiv preprint arXiv:2111.13606, 2021
[PDF]
[PDF]