Search Results for author: Giannis Daras

Found 17 papers, 12 papers with code

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

1 code implementation NeurIPS 2023 Giannis Daras, Kulin Shah, Yuval Dagan, Aravind Gollakota, Alexandros G. Dimakis, Adam Klivans

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples.

Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers

no code implementations6 Mar 2023 Sitan Chen, Giannis Daras, Alexandros G. Dimakis

We develop a framework for non-asymptotic analysis of deterministic samplers used for diffusion generative modeling.


Multiresolution Textual Inversion

1 code implementation30 Nov 2022 Giannis Daras, Alexandros G. Dimakis

We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions.

Soft Diffusion: Score Matching for General Corruptions

no code implementations12 Sep 2022 Giannis Daras, Mauricio Delbracio, Hossein Talebi, Alexandros G. Dimakis, Peyman Milanfar

To reverse these general diffusions, we propose a new objective called Soft Score Matching that provably learns the score function for any linear corruption process and yields state of the art results for CelebA.

Denoising Image Generation

Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems

2 code implementations18 Jun 2022 Giannis Daras, Yuval Dagan, Alexandros G. Dimakis, Constantinos Daskalakis

In practice, to allow for increased expressivity, we propose to do posterior sampling in the latent space of a pre-trained generative model.

Discovering the Hidden Vocabulary of DALLE-2

no code implementations1 Jun 2022 Giannis Daras, Alexandros G. Dimakis

We discover that DALLE-2 seems to have a hidden vocabulary that can be used to generate images with absurd prompts.

Solving Inverse Problems with NerfGANs

no code implementations16 Dec 2021 Giannis Daras, Wen-Sheng Chu, Abhishek Kumar, Dmitry Lagun, Alexandros G. Dimakis

We introduce a novel framework for solving inverse problems using NeRF-style generative models.


Robust Compressed Sensing MR Imaging with Deep Generative Priors

no code implementations NeurIPS Workshop Deep_Invers 2021 Ajil Jalal, Marius Arvinte, Giannis Daras, Eric Price, Alex Dimakis, Jonathan Tamir

The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems.

Robust Compressed Sensing MRI with Deep Generative Priors

2 code implementations NeurIPS 2021 Ajil Jalal, Marius Arvinte, Giannis Daras, Eric Price, Alexandros G. Dimakis, Jonathan I. Tamir

The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems.

Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

2 code implementations15 Feb 2021 Giannis Daras, Joseph Dean, Ajil Jalal, Alexandros G. Dimakis

We propose Intermediate Layer Optimization (ILO), a novel optimization algorithm for solving inverse problems with deep generative models.

Denoising Super-Resolution

SMYRF: Efficient Attention using Asymmetric Clustering

1 code implementation11 Oct 2020 Giannis Daras, Nikita Kitaev, Augustus Odena, Alexandros G. Dimakis

We also show that SMYRF can be used interchangeably with dense attention before and after training.

16k Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.