Blog(1)

• Fast and Accurate Inference in Variational Autoencoders

  Variational Autoencoders (VAE) [2,3] and Generative Adversarial Networks (GAN) [4] are the most popular deep generative models for high dimensional data (e.g., images).

Research Areas(0)

Publications(9)

• Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders

  AuthorMinyoung Kim

  PublishedComputer Vision and Pattern Recognition (CVPR)

  Date2022-06-21

• Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase

  AuthorAkhila Yerukola, Mason Bretan, Hongxia Jin

  PublishedEuropean Association for Computational Linguistics (EACL)

  Date2021-04-21

• Learning Intuitive Physics with Multimodal Generative Models

  AuthorSahand Rezaei-Shoshtari, Francois Robert Hogan, Michael Jenkin, David Meger, Gregory Dudek

  PublishedNational Conference on Artificial Intelligence (AAAI)

  Date2021-01-19

View More

News(2)

• [Blog] [CVPR 2022 Series #6] Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders

  Variational Autoencoder (VAE) [5,6] is one of the most popular deep latent variable models in modern machine learning. In VAE, we have a rich representational capacity to model a complex generative process of synthesizing images (x) from the latent variables (z).

• [Blog] Fast and Accurate Inference in Variational Autoencoders

  Variational Autoencoders (VAE) [2,3] and Generative Adversarial Networks (GAN) [4] are the most popular deep generative models for high dimensional data (e.g., images).

Others(0)