jaseleephd

nyu-thesis-template

NYU GSAS PhD thesis template

lanmt-ebm

lanmt ebm

backpack

BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.

kfac_pytorch

waveglow

A Flow-based Generative Network for Speech Synthesis

lanmt

LaNMT: Latent-variable Non-autoregressive Neural Machine Translation with Deterministic Inference

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

sylvester-flows

BNAF

Pytorch implementation of Block Neural Autoregressive Flow

vae_vampprior

Code for the paper "VAE with a VampPrior", J.M. Tomczak & M. Welling

flowseq

Generative Flow based Sequence-to-Sequence Toolkit written in Python.

ETM

Topic Modeling in Embedding Spaces

nsf

Code for Neural Spline Flows paper

dlmonitor

xlnet

XLNet: Generalized Autoregressive Pretraining for Language Understanding

REM

Reweighted Expectation Maximization

dl4dial-mt-beam

Supplementary materials and code for Multi-Turn Beam Search

dl4dial-bayesian-calibration

transformer-xl

nmtlab

A Pytorch-based Neural Machine Translation Framework for Research

seq2seq-con

Implementation of "Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs"

sacrebleu

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

MetaNMT

Meta learning for Neural Machine Translation

sa-vae

NAF

Experiments for the Neural Autoregressive Flows paper

Taming-VAEs

ShapeWorld

pytorch-trpo

PyTorch implementation of Trust Region Policy Optimization

pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

pytorch-meta-optimizer

A PyTorch implementation of Learning to learn by gradient descent by gradient descent