I am a post-doc at MIT CSAIL, working with Prof. Costantinos Daskalakis and Prof. Antonio Torralba.
Prior to that, I spent 4 wonderful years at UT Austin, working with Prof. Alexandros Dimakis.
Before starting my Ph.D., I received my undergraduate degree in ECE from the National Technical University of Athens (NTUA).
My research focuses on generative modeling, with a particular emphasis on learning from low-quality data sources—including corrupted, synthetic, and out-of-distribution samples. Broadly, I aim to squeeze as much signal as possible from whatever data is available.
News
- [Best Contribution Award]: Best Contribution Award at the International Biomedical and Astronomical Signal Processing (BASP) Frontiers Conference 2025.
- [Paper Acceptance]: How Much is a Noisy Image Worth? got accepted to ICLR 2025.
- [Paper Acceptance]: Ambient Diffusion Posterior Sampling got accepted to ICLR 2025.
- [Paper Acceptance]: Infilling Score got accepted to ICLR 2025.
Internships:
- NVIDIA Research (2023) with Arash Vahdat.
- Google Research (2022) with Peyman Milanfar, Mauricio Delbracio and Hossein Talebi.
- Google Research (2022) with Vincent Chu and Abhishek Kumar.
Talks
The most representative talk of my latest research is the one given at Columbia Engineering, as part of the Workshop on Emerging Trends in AI. Please watch the talk here.
For a full list of the talks that I have given over the years, see below.
Youtube Video
Youtube Video
Youtube Video
Youtube Video
Youtube Video
Youtube Video
Publications
For a more comprehensive list of publications, please visit my Google Scholar page.
Ambient Proteins: Training Diffusion Models on Low Quality Structures
Citation: Giannis Daras*, Jeffrey Ouyang-Zhang*, Krithika Ravishankar, William Daspit, Costis Daskalakis, Qiang Liu, Adam Klivans, Daniel J. Diaz, "Ambient Proteins: Training Diffusion Models on Low Quality Structures"
Ambient Diffusion Omni: Training Good Models with Bad Data
Citation: Giannis Daras*, Adrian Rodriguez-Munoz*, Adam Klivans, Antonio Torralba, Constantinos Daskalakis, "Ambient Diffusion Omni: Training Good Models with Bad Data"
How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion
Published in ICLR 2025 [Paper] [Code]
Citation: Giannis Daras, Yeshwanth Cherapanamjeri, Constantinos Daskalakis, "How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion", ICLR 2025
Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models
Published in ICLR 2025 [Paper]
Citation: Negin Raoof, Litu Rout, Giannis Daras, Sujay Sanghavi, Constantine Caramanis, Sanjay Shakkottai, Alexandros G. Dimakis, "Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models", ICLR 2025
Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data
Published in ICLR 2025 [Paper] [Code]
Citation: Asad Aali, Giannis Daras, Brett Levac, Sidharth Kumar, Alexandros G. Dimakis, Jonathan I. Tamir', "Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data", ICLR 2025
Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data
Published in ICML 2024 [Paper] [Code]
Citation: Giannis Daras, Alexandros G. Dimakis, Constantinos Daskalakis, "Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data", ICML 2024
Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models
Published in NeurIPS 2023 [Paper] [Code]
Citation: Litu Rout, Negin Raoof, Giannis Daras, Constantine Caramanis, Alexandros G. Dimakis, Sanjay Shakkottai, "Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models", NeurIPS 2023
Ambient Diffusion: Learning Clean Distributions from Corrupted Data
Published in NeurIPS 2023 [Paper] [Code]
Citation: Giannis Daras, Kulin Shah, Yuval Dagan, Aravind Gollakota, Alexandros G. Dimakis, Adam Klivans, "Ambient Diffusion: Learning Clean Distributions from Corrupted Data", NeurIPS 2023
DataComp: In search of the next generation of multimodal datasets
Published as an Oral in NeurIPS 2023 [Paper] [Code]
Citation: Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt, "DataComp: In search of the next generation of multimodal datasets", NeurIPS 2023
Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis for DDIM-Type Samplers
Published in ICML 2023 [Paper]
Citation: Sitan Chen, Giannis Daras, Alexandros G. Dimakis, "Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis for DDIM-Type Samplers", ICML 2023
Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent
Published in NeurIPS 2023 [Paper] [Code]
Citation: Giannis Daras, Yuval Dagan, Alexandros G. Dimakis, Constantinos Daskalakis, "Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent", NeurIPS 2023
Multiresolution Textual Inversion
Published as an Oral in NeurIPS 2022, SBM Workshop [Paper] [Code]
Citation: Giannis Daras, Alexandros G. Dimakis, "Multiresolution Textual Inversion", NeurIPS 2022, SBM Workshop
Soft Diffusion: Score Matching for General Corruptions
Published in TMLR 2023 [Paper]
Citation: Giannis Daras, Mauricio Delbracio, Hossein Talebi, Alexandros G. Dimakis, Peyman Milanfar, "Soft Diffusion: Score Matching for General Corruptions", TMLR 2023
Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems
Published in ICML 2022 [Paper] [Code]
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
Published in NeurIPS 2022 [Paper] [Code]
Citation: Giannis Daras (*) , Negin Raoof (*), Zoi Gkalitsiou, Alexandros G. Dimakis, "Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve", NeurIPS 2022
Discovering the Hidden Vocabulary of DALLE-2
Published in NeurIPS 2022 Workshop on Score-Based Methods [Paper]
Citation: Giannis Daras (*) , Alexandros G. Dimakis, "Discovering the Hidden Vocabulary of DALLE-2", NeurIPS 2022 Workshop on Score-Based Methods
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