Compute 2D human pose and angles from a video or a webcam.

MAGI-1: Autoregressive Video Generation at Scale

A high-throughput and memory-efficient inference and serving engine for LLMs

Disaggregated serving system for Large Language Models (LLMs).

Example models using DeepSpeed

Source code for Twitter's Recommendation Algorithm

中文LLaMA&Alpaca大语言模型+本地部署 (Chinese LLaMA & Alpaca LLMs)

Examples and guides for using the OpenAI API

Code and documentation to train Stanford's Alpaca models, and generate the data.

AcadHomepage: A Modern and Responsive Academic Personal Homepage

A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models

缠中说禅技术分析工具；缠论；股票；期货

Driving in CARLA using model-free deep reinforcement learning

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Code release of a paper "Guiding Deep Learning System Testing using Surprise Adequacy"

Trojan Attack on Neural Network

Statistical Learning Theory (CS229T) Lecture Notes

An experimental recommender alogrithm implementation using matlab/octave

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.