Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Lsyncd (Live Syncing Daemon) synchronizes local directories with remote targets

A torch implementation of http://arxiv.org/abs/1511.06434

Sequence-to-sequence model with LSTM encoder/decoders and attention

Neural Attention Model for Abstractive Summarization

Generative Adversarial Text-to-Image Synthesis

Character-level Convolutional Networks for Text Classification

LSTM language model with CNN over characters

Implementation of Variational Auto-Encoder in Torch7

Scripts and noise data for Belinkov & Bisk 2018