Giannis Daras

Faculty

Giannis Daras

Get in Touch

About

Academic Groups

Academic Area

Giannis Daras is an Assistant Professor at MIT Sloan as part of the Operations Research and Statistics group. Giannis obtained his PhD from the computer science Department of UT Austin under the supervision of Alex Dimakis and did his postdoc at MIT under the supervision of Antonio Torralba and Costis Daskalakis. 

 Giannis works on important practical and theoretical questions around deep generative models with a focus on training and sampling generative models in the presence of data corruption. 

He has been nominated as a Rising Star in AI by the University of Michigan, has earned the Best Contribution Award at the Biomedical and Astronomical Signal Processing (BASP) Conference, and has published 23 research papers (including 13 first-author works) at top-tier Machine Learning venues, including one Oral Presentation (top 0.3%) and two Spotlight presentations (top 3.2%) at NeurIPS. Giannis has also been supported by multiple fellowships, including the Graduate Dean’s Prestigious Fellowship (UT Austin), Onassis, Bodossakis, Leventis, and Gerondellis PhD Fellowships. His work has sparked the interest of the public following coverage by news outlets such as The Independent and the New York Post. His work has found applications across scientific fields such as Computer Vision, Computational Biology, Medical Imaging, Robotics, Economics, and Neuroscience.

Publications

"Ambient Dataloops: Generative Models for Dataset Refinement."

Adrian Rodriguez-Munoz, William Daspit, Adam Klivans, Antonio Torralba, Constantinos Daskalakis, and Giannis Daras. In 43rd International Conference on Machine Learning, Seoul, South Korea: July 2026. arXiv.

"Opt-In Art: Learning Art Styles Only from Few Examples."

Hui Ren, Joanna Materzynska, Rohit Gandikota, David Bau, and Antonio Torralba. San Diego, California: September 2025. arXiv.

"Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion."

Kulin Shah, Alkis Kalavasis, Adam Klivans, and Giannis Daras. In Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada: July 2025. arXiv.

"Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models."

Negin Raoof, Litu Rout, Giannis Daras, Sujay Sanghavi, Constantine Caramanis, Sanjay Shakkottai, and Alex Dimakis. In 13th International Conference on Learning Representations, Singapore: January 2025.

"Ambient Diffusion Omni: Training Good Models with Bad Data."

Giannis Daras, Adrian Rodriguez-Munoz, Adam Klivans, Antonio Torralba, and Constantinos Daskalakis. In Advances in Neural Information Processing Systems: Spotlight, San Diego, CA: 2025. Download Preprint.

"Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data."

Asad Aali, Giannis Daras, Brett Levac, Sidharth Kumar, Alexandros G. Dimakis, and Jon Tamir. In The Thirteenth International Conference on Learning Representations, 2025.

Load More