Human motion as foreign language.
-
Updated
Dec 6, 2023
Human motion as foreign language.
Basic models and their code in the field of image generation.
Official Code Repo for the paper "Learning to Play Atari in a World of Tokens" accepted at ICML, 2024
This presentation, conducted for the "Natural Language Processing" course, delves into the paper's content, which addresses the challenge of generating images for a story using a text-to-image framework. The paper can be accessed at https://arxiv.org/abs/2210.08465.
생성모델을 이용한 ASMR 컨텐츠 제작 프로젝트
Generative models nano version for fun. No STOA here, nano first.
A generative machine learning model that generates noval foley sounds
Generating images in different contexts using GANs and Variational Autoencoders
Discrete world modeling by recording Coppelia simulations with ROS
Medical Image Latent Space Visualization Using VQ-VAE
VQ-VAE-based image tokenizer for model-based RL
Conditional Video/GIF Synthesis implementation using PyTorch Lightning and Hydra. This method utilizes Vector Quantization Variational AutoEncoder (VQ-VAE) with Discrete Denoising Diffusion Probabilistic Models (D3PM) to generate novel videos.
Variational autoencoders implemented in Tensorflow.
This is a simplified implementation of VQ-GANs written in PyTorch. The architecture is borrowed from the paper "Taming Transformers for High-Resolution Image Synthesis".
Add a description, image, and links to the vq-vae topic page so that developers can more easily learn about it.
To associate your repository with the vq-vae topic, visit your repo's landing page and select "manage topics."