The official GitHub page for the survey paper "A Survey of Large Language Models".

Code from PLDI '21 paper "Provable Repair of Deep Neural Networks."

A paper list of lane detection.

An uncertainty-based random sampling algorithm for data augmentation

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

Repository with sample code and instructions for "Continuous Intelligence" and "Continuous Delivery for Machine Learning: CD4ML" workshops

MLNLP: This repository is a collection of AI top conferences papers (e.g. ACL, EMNLP, NAACL, COLING, AAAI, IJCAI, ICLR, NeurIPS, and ICML) with open resource code

Visualizations for machine learning datasets

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接

Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!

SC-FEGAN : Face Editing Generative Adversarial Network with User's Sketch and Color (ICCV2019)

A collection of infrastructure and tools for research in neural network interpretability.

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

One Shot Learning using Memory-Augmented Neural Networks (MANN) based on Neural Turing Machine architecture in Tensorflow

An experimental technique for efficiently exploring neural architectures.

A Platform for Many-Agent Reinforcement Learning

A method for training neural networks that are provably robust to adversarial attacks.

Repository to store conditional imitation learning based AI that runs on CARLA.

Reinforcement learning baseline agent trained with the Actor-critic (A3C) algorithm.

Open-source simulator for autonomous driving research.

The convertor/conversion of deep learning models for different deep learning frameworks/softwares.

Anomaly detection using deep neural network

A domain specific language to express machine learning workloads.

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

Torch implementation of DeepMask and SharpMask

Neural network model, suitable for multi-agent learning. https://arxiv.org/abs/1605.07736

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

The Atomic Game Engine is a multi-platform 2D and 3D engine with a consistent API in C++, C#, JavaScript, and TypeScript