Name: Vaidotas (Vaidas) Šimkus
Type: User
Company: University of Edinburgh
Bio: PhD candidate in Machine Learning at the University of Edinburgh. Interested in deep probabilistic models, probabilistic inference, and missing data problems.
Twitter: vsimkus
Location: Edinburgh
Blog: https://vsimkus.github.io
Vaidotas (Vaidas) Šimkus's Projects
An academic webpage template built on Jekyll-Now, designed with accessibility in mind. Preview available at https://vsimkus.github.io/academic-jekyll/.
[TMLR] Research code for the paper "Improving Variational Autoencoder Estimation from Incomplete Data with Mixture Variational Families".
A gnome-shell extension that adds submenu options access to Dell's Command Configure utility.
Joplin - an open source note taking and to-do application with synchronization capabilities for Windows, macOS, Linux, Android and iOS. Forum: https://discourse.joplinapp.org/
PyTorch data provider for Missing Data
Normalizing flows in PyTorch
An official repository for tutorials of Probabilistic Modelling and Reasoning (2023/2024) - a University of Edinburgh master's course.
An official repository for a PGM demo of Probabilistic Modelling and Reasoning (2023/2024) - a University of Edinburgh master's course.
An official repository for a VAE tutorial of Probabilistic Modelling and Reasoning (2023/2024) - a University of Edinburgh master's course.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
A fork of the Tmux powerline theme with small personal modifications
PyTorch implementation of the mixture distribution family with implicit reparametrisation gradients.
[TMLR] Research code for the paper "Conditional Sampling of Variational Autoencoders via Iterated Approximate Ancestral Sampling".
Voice conversion (VC) investigation using three variants of VAE
[JMLR] Research code for the paper "Variational Gibbs inference for statistical estimation from incomplete data".