DanHrmti / SenTransformer-VAE-pytorch
Sentence VAE using the Transformer encoder-decoder architecture.
☆9Updated 2 months ago
Alternatives and similar repositories for SenTransformer-VAE-pytorch:
Users that are interested in SenTransformer-VAE-pytorch are comparing it to the libraries listed below
- Transformer-based Conditional Variational Autoencoder for Controllable Story Generation☆151Updated 2 years ago
- Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.☆26Updated 3 years ago
- ☆39Updated 2 years ago
- This repository summarizes techniques for KL divergence vanishing problem.☆30Updated 5 years ago
- Bayesian Attention Modules☆35Updated 4 years ago
- Transformer-Based Conditioned Variational Autoencoder for Story Completion☆94Updated 4 years ago
- Code for "Finetuning Pretrained Transformers into Variational Autoencoders"☆37Updated 2 years ago
- Code and data for "Inferring Rewards from Language in Context" [ACL 2022].☆15Updated 2 years ago
- [ICML 2022] Latent Diffusion Energy-Based Model for Interpretable Text Modeling☆64Updated 2 years ago
- [ICLR'21] Counterfactual Generative Networks☆107Updated 3 years ago
- PyTorch implementation of the mixture distribution family with implicit reparametrisation gradients.☆19Updated last year
- This repo is for our paper "ControlVAE: Controllable Variational Autoencoder" published at ICML 2020. It can be used for text generation,…☆93Updated last year
- [ICLR 2022] code for "Towards building a group-based unsupervised representation disentanglement framework"☆15Updated 2 years ago
- Code for "World Model as a Graph: Learning Latent Landmarks for Planning" (ICML 2021 Long Presentation)☆66Updated 3 years ago
- This repo provides the code for the ACL 2020 paper "Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEnco…☆53Updated 4 years ago
- Transformer Variational Autoencoder experiment☆48Updated 5 years ago
- M-CURL: Masked Contrastive Representation Learning for Reinforcement Learning