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.
During Summer 2022, I interned 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.
Publications
Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems
Published in ICML 2022 [Paper]
Citation: Giannis Daras (*) , Yuval Dagan (*), Alexandros G. Dimakis, Constantinos Daskalakis, "Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems" , ICML 2022
Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve
Preprint [Paper]
Citation: Giannis Daras (*) , Negin Raoof (*), Zoi Gkalitsiou, Alexandros G. Dimakis, "Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve"
Discovering the Hidden Vocabulary of DALLE-2
Preprint [Paper]
Citation: Giannis Daras (*) , Alexandros G. Dimakis, "Discovering the Hidden Vocabulary of DALLE-2"
Solving Inverse Problems with NerfGANs
Preprint [Paper]
Citation: Giannis Daras, Wen-Sheng Chu, Abhishek Kumar, Dmitry Lagun, Alexandros G. Dimakis, "Solving Inverse Problems with NerfGANs"
Robust Compressed Sensing MRI with Deep Generative Priors
Published in NeurIPS 2021 [Paper] [Code]
Citation: Ajil Jalal, Marius Arvinte, Giannis Daras , Eric Price, Alexandros G. Dimakis, Jonathan I. Tamir, "Robust Compressed Sensing MRI with Deep Generative Priors" , NeurIPS 2021
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
Published in ICML 2021 [Paper] [Code]
Citation: Giannis Daras , Joseph Dean, Ajil Jalal, Alexandros G. Dimakis, "Intermediate Layer Optimization for Inverse Problems using Deep Generative Models" , ICML 2021
SMYRF: Efficient Attention using Asymmetric Clustering
Published in NeurIPS 2020 [Paper] [Code]
Citation: Giannis Daras, Nikita Kitaev, Augustus Odena, Alexandros G. Dimakis, "SMYRF: Efficient Attention using Asymmetric Clustering" , NeurIPS 2020
Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models
Published in CVPR 2020 [Paper] [Code]
Citation: Giannis Daras, Augustus Odena, Han Zhang, Alexandros G. Dimakis, "Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models" , CVPR 2020