Search Results for author:
Found 6 papers, 3 papers with code
LTX-Video: Realtime Video Latent Diffusion
To address this, our VAE decoder is tasked with both latent-to-pixel conversion and the final denoising step, producing the clean result directly in pixel space.
V-LASIK: Consistent Glasses-Removal from Videos Using Synthetic Data
We show that despite data imperfection, by learning from our generated data and leveraging the prior of pretrained diffusion models, our model is able to perform the desired edit consistently while preserving the original video content.
When Is Unsupervised Disentanglement Possible?
In this paper, we show that the assumption of local isometry together with non-Gaussianity of the factors, is sufficient to provably recover disentangled representations from data.
The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation is an inherently ill-posed problem.
A Bayes-Optimal View on Adversarial Examples
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 training methods or an inevitable "feature" of high dimensional geometry.
On GANs and GMMs
While GMMs have previously been shown to be successful in modeling small patches of images, we show how to train them on full sized images despite the high dimensionality.
