Explore >> Select a destination
|
You are here 
|
www.v7labs.com | ||
| | | | |
goodfire.ai
|
|
| | | | | Goodfire is an AI research company building practical interpretability tools for safe and reliable generative models. | |
| | | | |
blog.otoro.net
|
|
| | | | | [AI summary] This text discusses the development of a system for generating large images from latent vectors, combining Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). It explores the use of Conditional Perceptual Neural Networks (CPPNs) to create images with specific characteristics, such as style and orientation, by manipulating latent vectors. The text also covers the ability to perform arithmetic on latent vectors to generate new images and the potential for creating animations by transitioning between different latent states. The author suggests future research directions, including training on more complex datasets and exploring alternative training objectives beyond Maximum Likelihood. | |
| | | | |
tech.preferred.jp
|
|
| | | | | This article is contributed by Jinzhe Zhang, who worked for the 2021 PFN Summer Internship. Introduction The traditional drug discovery technique often | |
| | | | |
blog.evjang.com
|
|
| | | This is a tutorial on common practices in training generative models that optimize likelihood directly, such as autoregressive models and ... | ||
