Eitan Richardson
YOU?
Author Swipe
View article: LTX-Video: Realtime Video Latent Diffusion
LTX-Video: Realtime Video Latent Diffusion Open
We introduce LTX-Video, a transformer-based latent diffusion model that adopts a holistic approach to video generation by seamlessly integrating the responsibilities of the Video-VAE and the denoising transformer. Unlike existing methods, …
View article: The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation
The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation Open
Unsupervised image-to-image translation is an inherently ill-posed problem. Recent methods based on deep encoder-decoder architectures have shown impressive results, but we show that they only succeed due to a strong locality bias, and the…
View article: A Bayes-Optimal View on Adversarial Examples
A Bayes-Optimal View on Adversarial Examples Open
Since the discovery of adversarial examples - the ability to fool modern CNN classifiers with tiny perturbations of the input, there has been much discussion whether they are a "bug" that is specific to current neural architectures and tra…
View article: On GANs and GMMs
On GANs and GMMs Open
A longstanding problem in machine learning is to find unsupervised methods that can learn the statistical structure of high dimensional signals. In recent years, GANs have gained much attention as a possible solution to the problem, and in…
View article: On GANs and GMMs
On GANs and GMMs Open
A longstanding problem in machine learning is to find unsupervised methods that can learn the statistical structure of high dimensional signals. In recent years, GANs have gained much attention as a possible solution to the problem, and in…
View article: On GANs and GMMs
On GANs and GMMs Open
A longstanding problem in machine learning is to find unsupervised methods that can learn the statistical structure of high dimensional signals. In recent years, GANs have gained much attention as a possible solution to the problem, and in…