Mingcong-Cao
Follow
Stars
Evaluating long-term memory of reinforcement learning algorithms
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Cuda installation on WSL2 Ubuntu 20.04 and Windows11
A simple and efficient Mamba implementation in pure PyTorch and MLX.
Mastering Diverse Domains through World Models
PyTorch implementation of "Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs", NeurIPS 2020
About repo with information useful for the Fall 2024 offering of ECE 759 - High Performance Computing for Applications in Engineering
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet…
Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]
Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.
A PyTorch implementation of EfficientNet
A collection of C/C++ programs and Python scripts to be used in conjunction with Intel Software Development Emulator (Intel SDE, available externally separately). The purpose is to use record/repla…
A customizable hardware prefetching framework using online reinforcement learning as described in the MICRO 2021 paper by Bera et al. (https://arxiv.org/pdf/2109.12021.pdf).
ChampSim is an open-source trace based simulator maintained at Texas A&M University and through the support of the computer architecture community.
⚡ Flashbax: Accelerated Replay Buffers in JAX
The purpose of this repo is to make it easy to get started with JAX, Flax, and Haiku. It contains my "Machine Learning with JAX" series of tutorials (YouTube videos and Jupyter Notebooks) as well a…
A novel preference-driven multi-objective reinforcement learning algorithm using a single policy network that covers the entire preference space in a given domain.
Playing Mountain-Car without reward engineering, by combining DQN and Random Network Distillation (RND)
Multi-Objective Reinforcement Learning algorithms implementations.
Implementation and improvement of "Over the Air Deep Learning Based Radio Signal Classification"
Final Project for AI Wireless
Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
p5.js is a client-side JS platform that empowers artists, designers, students, and anyone to learn to code and express themselves creatively on the web. It is based on the core principles of Proces…
A Cooperative Voice Analysis Repository for Speech Technologies
M-SENA: All-in-One Platform for Multimodal Sentiment Analysis