Applying Reinforcement Learning from Human Feedback to language models to teach them to write short story responses to writing prompts.

Python 3.8+ toolbox for submitting jobs to Slurm

This is a fork of the awesome Joey-NMT with Reinforcement Learning algorithms like Policy Gradient, MRT and Advantage Actor Critic.

Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.

MLE-Guided Parameter Search (AAAI 2021)

Discontinuous Hamiltonian Monte Carlo in JAX

PyTorch original implementation of Cross-lingual Language Model Pretraining.

Unsupervised Statistical Machine Translation

The Return of Lexical Dependencies: Neural Lexicalized PCFGs (TACL)

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019

Code to reproduce experiments in the paper "Task-Oriented Dialogue as Dataflow Synthesis" (TACL 2020).

From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction

Reinforcement Learning for Neural Machine Translation

Compositional generalization through meta sequence-to-sequence learning

Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for natural language modeling fail when such compositional generali…

Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch

pytorch implementation of "Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control"

Python Multi-Agent Reinforcement Learning framework

EGG: Emergence of lanGuage in Games

Code for Emergent Translation in Multi-Agent Communication

Code associated with the Don't Stop Pretraining ACL 2020 paper

A neural machine translation model in PyTorch

Implementation of Dual Learning NMT on PyTorch

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Code for "Unsupervised State Representation Learning in Atari"

Graph-based Deep Q Network for Web Navigation

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)