Constantinos Costis Daskalakis

Learning Correlated Reward Models: Statistical Barriers and Opportunities

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization

Ambient Dataloops: Generative Models for Dataset Refinement

Bidding for Influence: Auction-Driven Diffusion Image Generation

Ambient Proteins - Training Diffusion Models on Noisy Structures

Learning Gaussian DAG Models without Condition Number Bounds

Ambient Diffusion Omni: Training Good Models with Bad Data

How Much is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion.