collaborators

7 papers

cs.CV2026

Seeing Through the PRISM: Compound & Controllable Restoration of Scientific Images

Rupa Kurinchi-Vendhan, Pratyusha Sharma, Antonio Torralba +1

Scientific and environmental imagery often suffer from complex mixtures of noise related to the sensor and the environment. Existing restoration methods typically remove one degrad…

cs.CV2026

Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

Hila Chefer, Patrick Esser, Dominik Lorenz +5

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require sepa…

cs.LG2026

Ambient Dataloops: Generative Models for Dataset Refinement

Adrián Rodríguez-Muñoz, William Daspit, Adam Klivans +3

We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets cont…

cs.LG2025

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

Danial Hosseintabar, Fan Chen, Giannis Daras +2

Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains…

cs.CV2025

Dataset Distillation for Pre-Trained Self-Supervised Vision Models

George Cazenavette, Antonio Torralba, Vincent Sitzmann

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larg…

cs.GR2025

Ambient Diffusion Omni: Training Good Models with Bad Data

Giannis Daras, Adrian Rodriguez-Munoz, Adam Klivans +2

We show how to use low-quality, synthetic, and out-of-distribution images to improve the quality of a diffusion model. Typically, diffusion models are trained on curated datasets t…