I am a second year Computer Science Ph.D. student at UT Austin, supervised by Prof. Alexandros Dimakis.

I am doing research on deep generative models. My main goal is to explore the theoretical and practical limits of solving inverse problems using deep generative priors. I am interested in improving many aspects of deep generative models that could be useful for achieving that goal, such as fairness, high-quality sample generation, out-of-distribution generation, controllable synthesis, etc. Application wise, I hope that my research on inverse problems with generative priors will prove useful to important real-world applications, e.g. MRI scans.

Currently, I am interning at Google Research with Peyman Milanfar, Mauricio Delbracio and Hossein Talebi. Prior to this internship, I worked as a Research Intern at Google with Vincent Chu and Abhishek Kumar. Before joining the Ph.D., I received my undergraduate degree in ECE from the National Technical University of Athens (NTUA). During my undergraduate studies, I worked as a Machine Learning Researcher in ExplosionAI and I successfully completed Google Summer of Code 2018.

News

  • [New paper]: We discovered that DALLE-2 has a secret vocabulary. We wrote a paper summarizing our findings. Find the paper here.
  • [New paper]: Our paper, Score-Guided Intermediate Layer Optimization, got accepted to ICML 2022. Camera-ready version coming soon.
  • [Personal update]: I am interning at Google Research for the summer. I am working with Peyman Milanfar, Mauricio Delbracio and Hossein Talebi.

Publications