zheng-yanan / techniques-for-kl-vanishingLinks
This repository summarizes techniques for KL divergence vanishing problem.
☆30Updated 6 years ago
Alternatives and similar repositories for techniques-for-kl-vanishing
Users that are interested in techniques-for-kl-vanishing are comparing it to the libraries listed below
Sorting:
- ☆198Updated 3 years ago
- Transformer Variational Autoencoder experiment☆50Updated 6 years ago
- Variational Transformers for Diverse Response Generation☆82Updated last year
- pytorch implementation of VAE-Gumble-Softmax☆63Updated 5 years ago
- A curated list of techniques to avoid posterior collapse☆85Updated 2 years ago
- A Pytorch implementation of the optimal transport kernel embedding☆118Updated 4 years ago
- This repo is for our paper "ControlVAE: Controllable Variational Autoencoder" published at ICML 2020. It can be used for text generation,…☆95Updated 2 years ago
- Transformer-Based Conditioned Variational Autoencoder for Story Completion☆94Updated 5 years ago
- Neural State Machine implemented in PyTorch☆71Updated 6 years ago
- Variational Autoencoder with Spatial Broadcast Decoder☆35Updated 6 years ago
- [ICML 2022] Latent Diffusion Energy-Based Model for Interpretable Text Modeling☆67Updated 3 years ago
- Implementation of Sparsemax activation in Pytorch☆166Updated 5 years ago
- SparseMax activation function implementation (ICML 2016) (PyTorch)☆28Updated 8 years ago
- Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation☆69Updated 5 years ago
- ☆27Updated 5 years ago
- ☆36Updated 5 years ago
- ☆33Updated 6 years ago
- Hybrid Discriminative-Generative Training via Contrastive Learning☆75Updated 2 years ago
- implements optimal transport algorithms in pytorch☆102Updated 3 years ago
- Transformer-based Conditional Variational Autoencoder for Controllable Story Generation☆161Updated 3 years ago
- ☆24Updated 4 years ago
- This is a PyTorch implementation of the ICLR 2017 paper "HIERARCHICAL MULTISCALE RECURRENT NEURAL NETWORKS" (https://openreview.net/pdf?i…☆51Updated 7 years ago
- ReaSCAN is a synthetic navigation task that requires models to reason about surroundings over syntactically difficult languages. (NeurIPS…☆19Updated 4 years ago
- Code to reproduce the results for Compositional Attention☆59Updated 3 years ago
- Code for the paper PermuteFormer☆42Updated 4 years ago
- PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World [ACL 2021]☆57Updated 4 years ago
- Z Forcing: Training Stochastic RNN's, NIPS'17☆33Updated 8 years ago
- Implementation of the MMD VAE paper (InfoVAE: Information Maximizing Variational Autoencoders) in pytorch☆43Updated 5 years ago
- Implementation of Stochastic Beam Search using Fairseq☆105Updated 6 years ago
- Hyperbolic Neural Networks, pytorch☆87Updated 6 years ago