NYU GSAS PhD thesis template

lanmt ebm

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

A Flow-based Generative Network for Speech Synthesis

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

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

Pytorch implementation of Block Neural Autoregressive Flow

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

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

Topic Modeling in Embedding Spaces

Code for Neural Spline Flows paper

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Reweighted Expectation Maximization

Supplementary materials and code for Multi-Turn Beam Search

A Pytorch-based Neural Machine Translation Framework for Research

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

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

Meta learning for Neural Machine Translation

Experiments for the Neural Autoregressive Flows paper

PyTorch implementation of Trust Region Policy Optimization

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKT…

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