Daskalakis, Constantinos Costis

6 publications

NeurIPS 2025 Ambient Diffusion Omni: Training Good Models with Bad Data Giannis Daras, Adrian Rodriguez-Munoz, Adam Klivans, Antonio Torralba, Constantinos Costis Daskalakis

NeurIPS 2025 Ambient Proteins - Training Diffusion Models on Noisy Structures Giannis Daras, Jeffrey Ouyang-Zhang, Krithika Ravishankar, Constantinos Costis Daskalakis, Adam Klivans, Daniel Jesus Diaz

ICLR 2025 How Much Is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion. Giannis Daras, Yeshwanth Cherapanamjeri, Constantinos Costis Daskalakis

ICML 2025 Learning Gaussian DAG Models Without Condition Number Bounds Constantinos Costis Daskalakis, Anthimos Vardis Kandiros, Rui Yao

AISTATS 2025 Learning High-Dimensional Gaussians from Censored Data Arnab Bhattacharyya, Constantinos Costis Daskalakis, Themis Gouleakis, Yuhao Wang

ICML 2024 Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data Giannis Daras, Alex Dimakis, Constantinos Costis Daskalakis