zheng-yanan / techniques-for-kl-vanishing
This repository summarizes techniques for KL divergence vanishing problem.
☆29Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for techniques-for-kl-vanishing
- Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation☆69Updated 3 years ago
- Variational Transformers for Diverse Response Generation☆82Updated 4 months ago
- A Pytorch implementation of the optimal transport kernel embedding☆114Updated 3 years ago
- Hybrid Discriminative-Generative Training via Contrastive Learning☆75Updated last year
- ☆36Updated 4 years ago
- pytorch implementation of VAE-Gumble-Softmax☆62Updated 4 years ago
- This repo is for our paper "ControlVAE: Controllable Variational Autoencoder" published at ICML 2020. It can be used for text generation,…☆91Updated last year
- [ICLR 2020] FSPool: Learning Set Representations with Featurewise Sort Pooling☆42Updated last year
- Neural State Machine implemented in PyTorch☆70Updated 5 years ago
- ☆187Updated 2 years ago
- ☆39Updated 2 years ago
- Transformer-Based Conditioned Variational Autoencoder for Story Completion☆94Updated 4 years ago
- Tensorflow implementation of "Meta Dropout: Learning to Perturb Latent Features for Generalization" (ICLR 2020)☆27Updated 4 years ago
- Transformer Variational Autoencoder experiment☆49Updated 5 years ago
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆43Updated last year
- code for paper "Improving Sequence-to-Sequence Learning via Optimal Transport"☆68Updated 5 years ago
- This repository hosts the dataset and source code for "A causal view of compositional zero-shot recognition". Yuval Atzmon, Felix Kreuk, …☆27Updated 3 years ago
- Code for reversible recurrent neural networks☆38Updated 5 years ago
- ☆23Updated 3 years ago
- ICML 2020, Estimating Generalization under Distribution Shifts via Domain-Invariant Representations☆21Updated 4 years ago
- ☆27Updated 4 years ago
- Implementation of the MMD VAE paper (InfoVAE: Information Maximizing Variational Autoencoders) in pytorch☆42Updated 4 years ago
- Project page for paper Self-supervised Representation Learning with Relative Predictive Coding☆17Updated 3 years ago
- ☆12Updated 3 years ago
- Transformer-based Conditional Variational Autoencoder for Controllable Story Generation☆146Updated 2 years ago
- PyTorch implementation of NICE☆33Updated 5 years ago
- Hyperbolic Neural Networks, pytorch☆84Updated 5 years ago
- Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for nat…☆27Updated 4 years ago
- Z Forcing: Training Stochastic RNN's, NIPS'17☆32Updated 7 years ago
- [ICML 2022] Latent Diffusion Energy-Based Model for Interpretable Text Modeling☆63Updated 2 years ago