Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning

Implementation of "Disentangled Representation Learning for Non-Parallel Text Style Transfer(ACL 2019)" in Pytorch

This repository contains the implementation of SimplEx, a method to explain the latent representations of black-box models with the help of a corpus of examples. For more details, please read our NeurIPS 2021 paper: 'Explaining Latent Representations with a Corpus of Examples'.

Code for our paper -- Hyperprior Induced Unsupervised Disentanglement of Latent Representations (AAAI 2019)

Tripod is a tool/ML model for computing latent representations for large sequences

ICCV23 "Householder Projector for Unsupervised Latent Semantics Discovery"

Variational Interpretable Concept Embeddings

Code associated with the paper "Prior Image-Constrained Reconstruction using Style-Based Generative Models" accepted to ICML 2021.

Investigate mapping of articulations from the image space to the latent space using neural networks.

Working towards deliverable 5.3

Latent-Explorer is the Python implementation of the framework proposed in the paper "Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph".

This algorithm exploits the relationships between variables to improve the reconstruction performance of the variational autoencoder (VAE). A correlation score was used as the metric to group the features via a distance-based clustering method. The resulting clusters served as inputs for the Attention-Based VAE.