lewisKit

stable-diffusion

A latent text-to-image diffusion model

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

HumanSystemOptimization

健康学习到150岁 - 人体系统调优不完全指南

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

mesh-transformer-jax

Model parallel transformers in JAX and Haiku

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

RL4LMs

A modular RL library to fine-tune language models to human preferences

pml2-book

Probabilistic Machine Learning: Advanced Topics

video-diffusion-pytorch

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

VQ-Diffusion

Official implementation of VQ-Diffusion

GODEL

Large-scale pretrained models for goal-directed dialog

robomimic

robomimic: A Modular Framework for Robot Learning from Demonstration

AFNO-transformer

Adaptive FNO transformer - official Pytorch implementation

nash-mtl

Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]

dreamer-pytorch

pytorch-implementation of Dreamer (Model-based Image RL Algorithm)

BERT-Tickets

[NeurIPS 2020] "The Lottery Ticket Hypothesis for Pre-trained BERT Networks", Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Zhangyang Wang, Michael Carbin

denoised_mdp

Open source code for paper "Denoised MDPs: Learning World Models Better Than the World Itself"

Pre-Trained-Language-Models-for-Interactive-Decision-Making

Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]

MUST

PyTorch code for MUST

long_seq_mae

code release of research paper "Exploring Long-Sequence Masked Autoencoders"

genesis

Official PyTorch implementation of GENESIS and GENESIS-V2

Quark

instructrl

Instruction Following Agents with Multimodal Transforemrs

eirli

An Empirical Investigation of Representation Learning for Imitation (EIRLI), NeurIPS'21

poisson_quasimetric_embedding

Open source code for paper "On the Learning and Learnability of Quasimetrics".

ToDCL

Continual Learning for Task-Oriented Dialogue Systems

rainier

oreo

imitation-dice