Kawase Yoshiaki

genai-web. 源内Web（AIインターフェース）

triton. Development repository for the Triton language and compiler

offload_adam. Python

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

apex. A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

tabm. (ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling

moment. MOMENT: A Family of Open Time-series Foundation Models, ICML'24

BitNet. Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

LLM-scientific-feedback. Can large language models provide useful feedback on research papers? A large-scale empirical analysis.

xla. Enabling PyTorch on XLA Devices (e.g. Google TPU)

torchquantum. A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum computers.

orqviz. Python package for visualizing the loss landscape of parameterized quantum algorithms.

quantum-algorithms-benchmarks. Jupyter Notebook

qiskit-machine-learning. An open-source library built on Qiskit for quantum machine learning tasks at scale on quantum hardware and classical simulators

qiskit-dynamics. DEPRECATED - Tools for building and solving models of quantum systems in Qiskit

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

stable-diffusion-webui. Stable Diffusion web UI

sd-webui-controlnet. WebUI extension for ControlNet

automl. Google Brain AutoML

DiffusionToolkit. Metadata-indexer and Viewer for AI-generated images

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

Live3D-v2. Neural Rendering with Attention: An Incremental Improvement for Anime Character Animation

NVTabular. NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

alphatensor. Python

stable-diffusion. A latent text-to-image diffusion model

ImHex. 🔍 A Hex Editor for Reverse Engineers, Programmers and people who value their retinas when working at 3 AM.

asp-tutorial-2022. Ono laboratory audio signal processing exercise for beginners.

mml-book.github.io. Companion webpage to the book "Mathematics For Machine Learning"

cis6930-fall2021. Course materials for Fall 2021 "CIS6930 Topics in Computing for Data Science" at New College of Florida

dtreeviz. A python library for decision tree visualization and model interpretation.

ffcv. FFCV: Fast Forward Computer Vision (and other ML workloads!)

TorchSSL. A PyTorch-based library for semi-supervised learning (NeurIPS'21)

jaxopt. Hardware accelerated, batchable and differentiable optimizers in JAX.

nccl. Optimized primitives for collective multi-GPU communication

FLAML. A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

gpufort. GPUFORT: S2S translation tool for CUDA Fortran and Fortran+X in the spirit of hipify

xfeat. Flexible Feature Engineering & Exploration Library using GPUs and Optuna.

The-Art-of-Linear-Algebra. Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"

single-parameter-fit. Real numbers, data science and chaos: How to fit any dataset with a single parameter

optax. Optax is a gradient processing and optimization library for JAX.

flax. Flax is a neural network library for JAX that is designed for flexibility.

Merlion. Merlion: A Machine Learning Framework for Time Series Intelligence

jupyterlab-desktop. JupyterLab desktop application, based on Electron.

deq. [NeurIPS'19] Deep Equilibrium Models

pytorch_geometric. Graph Neural Network Library for PyTorch

loss-landscape. Code for visualizing the loss landscape of neural nets

scikit-qulacs. scikit-qulacs is a library for quantum neural network. This library is based on qulacs and named after scikit-learn.

chemical_vae. Code for 10.1021/acscentsci.7b00572, now running on Keras 2.0 and Tensorflow

low-level-programming. Source code for 'Low-Level Programming' by Igor Zhirkov

brax. Massively parallel rigidbody physics simulation on accelerator hardware.

deduplicate-text-datasets. Rust

dl-visuals. Over 200 figures and diagrams of the most popular deep learning architectures and layers FREE TO USE in your blog posts, slides, presentations, or papers.

g-mlp-pytorch. Implementation of gMLP, an all-MLP replacement for Transformers, in Pytorch

shap. A game theoretic approach to explain the output of any machine learning model.

HandyRL. HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.

QTensorNet. Python

sam. SAM: Sharpness-Aware Minimization (PyTorch)

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

sam. Python

Python. All Algorithms implemented in Python

DistilBERT-base-jp.

qsim. Fast C++ and Python library for state-vector simulation of quantum circuits.

quantum. An open-source Python framework for hybrid quantum-classical machine learning.

enoki. Enoki: structured vectorization and differentiation on modern processor architectures

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

kit. 🧱 Describe your site, AI builds it, you own it as Markdown. Snap together Tailwind blocks like Lego — landing pages, blogs, portfolios, docs & more. No AI slop. Free to deploy anywhere 👇

graphillion. Fast, lightweight graphset operation library

python-quaec. A library for working with quantum error correction.

vdb. Vtuber Database

syk. Numerical simulation of the Sachdev-Ye-Kitaev fermion model

qflex. Flexible Quantum Circuit Simulator (qFlex) implements an efficient tensor network, CPU-based simulator of large quantum circuits.

pyqubo. Python DSL for constructing QUBOs from mathematical expressions.

Yao.jl. Extensible, Efficient Quantum Algorithm Design for Humans.

kaggle-cli. Official Kaggle CLI

WolframLanguageForJupyter. Wolfram Language kernel for Jupyter notebooks

OpenJij. OpenJij : Framework for the Ising model and QUBO.

tf-quant-finance. High-performance TensorFlow library for quantitative finance.

DeepGBM. SIGKDD'2019: DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks

AutoSmart. Python

Quantum. Microsoft Quantum Development Kit Samples

dlbook_exercises. Exercises for the Deep Learning textbook at www.deeplearningbook.org

pennylane. PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.

fklearn. fklearn: Functional Machine Learning

EconML. ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its goals is to build a toolkit that combines state-of-the-art machine learning techniques with econometrics in order to bring automation to complex causal inference problems. To date, the ALICE Python SDK (econml) implements orthogonal machine learning algorithms such as the double machine learning work of Chernozhukov et al. This toolkit is designed to measure the causal effect of some treatment variable(s) t on an outcome variable y, controlling for a set of features x.

lingvo. Lingvo

FavoritePapers.

neural-mmo. Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"

liboqs. C library for prototyping and experimenting with quantum-resistant cryptography

tsne-cuda. GPU Accelerated t-SNE for CUDA with Python bindings

PlotNeuralNet. Latex code for making neural networks diagrams

recommenders. Best Practices on Recommendation Systems

merf. Mixed Effects Random Forest

thundersvm. ThunderSVM: A Fast SVM Library on GPUs and CPUs

thundergbm. ThunderGBM: Fast GBDTs and Random Forests on GPUs

hypertools. A Python toolbox for gaining geometric insights into high-dimensional data

qvm. The high-performance and featureful Quil simulator.

generative-models. Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

obstacle-tower-env. Obstacle Tower Environment

baby-steps-of-rl-ja. Pythonで学ぶ強化学習 -入門から実践まで- サンプルコード

tetris_mcts. MCTS project for Tetris

PhysX-3.4. NVIDIA PhysX SDK 3.4

optuna. A hyperparameter optimization framework

teachable-machine-boilerplate. Boilerplate code for Teachable Machine

cub. [ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

keras-attention. Keras Attention Layer (Luong and Bahdanau scores).

cesium. Machine Learning Time-Series Platform

openTSNE. Extensible, parallel implementations of t-SNE

ailab. Experience, Learn and Code the latest breakthrough innovations with Microsoft AI

TernausNet. UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset

scikit-tda. Topological Data Analysis for Python🐍

OpenFermion-Cirq. Quantum circuits for simulations of quantum chemistry and materials.

Cirq. Python framework for creating, editing, and running Noisy Intermediate-Scale Quantum (NISQ) circuits.

fairlearn. A Python package to assess and improve fairness of machine learning models.

grf. Generalized Random Forests

Deep-Reinforcement-Learning-Hands-On. Hands-on Deep Reinforcement Learning, published by Packt

zapcc. zapcc is a caching C++ compiler based on clang, designed to perform faster compilations

qiskit-js. :atom_symbol: Qiskit (Quantum Information Science Kit) for JavaScript

qiskit-aqua. Quantum Algorithms & Applications (**DEPRECATED** since April 2021 - see readme for more info)

OpenFermion. Python package for compiling and analyzing quantum algorithms to simulate electronic structures.

flutter. Flutter makes it easy and fast to build beautiful apps for mobile and beyond

keras-js. Run Keras models in the browser, with GPU support using WebGL

tfjs-examples. Examples built with TensorFlow.js

tensorflow-XNN. 4th Place Solution for Mercari Price Suggestion Competition on Kaggle using DeepFM variant.

h2o4gpu. H2Oai GPU Edition

openqasm. Quantum assembly language for extended quantum circuits

irr. Better implementation of numpy.irr

qpic. Creating quantum circuit diagrams in TikZ

ctf. Cyclops Tensor Framework: parallel arithmetic on multidimensional arrays

quantpycupy. Python

grove. Quantum algorithms built using pyQuil.

pyquil. A Python library for quantum programming using Quil.

DQN-tensorflow. Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

Arcade-Learning-Environment. A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games

models. Models and examples built with TensorFlow

learning-to-learn. Learning to Learn in TensorFlow

sonnet. TensorFlow-based neural network library

catboost. A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

infiniteboost. InfiniteBoost: building infinite ensembles with gradient descent

d3. Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:

techan.js. A visual, technical analysis and charting (Candlestick, OHLC, indicators) library built on D3.

kaggle-dstl. Kaggle DSTL Satellite Imagery Feature Detection

StackNet. StackNet is a computational, scalable and analytical Meta modelling framework

kaggle-satellite-imagery-feature-detection. 9th place solution in "Dstl Satellite Imagery Feature Detection"

faiss. A library for efficient similarity search and clustering of dense vectors.

deep-forest. An on going implementation of the gcForest algorithm

lightgbm-gpu. Development Repository for GPU-accelerated GBDT training

tflearn. Deep learning library featuring a higher-level API for TensorFlow.

light-ffm. C++

minpy. NumPy interface with mixed backend execution

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

kaggle-past-solutions. A searchable compilation of Kaggle past solutions

thrust. [ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl

kaggle-allstate-claims-severity. 2nd place solution for Allstate Claims Severity competition at Kaggle

kaggle-seizure-prediction-challenge-2016. Code and documentation for the winning solution to the Melbourne University AES/MathWorks/NIH Seizure Prediction challenge on kaggle

deep-learning-models. Keras code and weights files for popular deep learning models.

torch7. http://torch.ch

tensorflow. An Open Source Machine Learning Framework for Everyone

fb.resnet.torch. Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

videogan. Generating Videos with Scene Dynamics. NIPS 2016.

tgboost. Tiny Gradient Boosting Tree

caretEnsemble. caret models all the way down :turtle:

bitcoin. Bitcoin Core integration/staging tree

pyLightGBM. Python binding for Microsoft LightGBM

Multicore-TSNE. Parallel t-SNE implementation with Python and Torch wrappers.

LightGBM. A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

coding-interview-university. A complete computer science study plan to become a software engineer.

reinforcement-learning. Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

wavenet. Keras WaveNet implementation

fast-wavenet. Speedy Wavenet generation using dynamic programming :zap:

FastBDT. Stochastic Gradient Boosted Decision Trees as Standalone, TMVAPlugin and Python-Interface

fast_rgf. Multi-core implementation of Regularized Greedy Forest

nnvm. C++

kaggle-distracted-driver-detection. 10th place solution in "State Farm Distracted Driver Detection"

xgbfir. XGBoost Feature Interactions Reshaped

LargeVis. C++

Probabilistic-Programming-and-Bayesian-Methods-for-Hackers. aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

rgf. Home repository for the Regularized Greedy Forest (RGF) library. It includes original implementation from the paper and multithreaded one written in C++, along with various language-specific wrappers.

theano_exercises. Exercises for my tutorials on Theano

atari-ai. C++

pymc. Bayesian Modeling and Probabilistic Programming in Python

nvidia-docker. Build and run Docker containers leveraging NVIDIA GPUs

darkforestGo. DarkForest, the Facebook Go engine.

ultrasound-nerve-segmentation. Deep Learning Tutorial for Kaggle Ultrasound Nerve Segmentation competition, using Keras

Net2Net. numpy implementation of net 2 net from the paper Net2Net: Accelerating Learning via Knowledge Transfer http://arxiv.org/abs/1511.05641

Gikou. 将棋ソフト「技巧」

tffm. TensorFlow implementation of an arbitrary order Factorization Machine

kaggle-coupon-purchase-prediction. Code for RECRUIT Challenge. 5th place.

RGF-sklearn. Scikit-learn API toy wrapper for Regularized Greedy Forests

gym. A toolkit for developing and comparing reinforcement learning algorithms.

kaggle-airbnb-recruiting-new-user-bookings. 2nd Place Solution in Kaggle Airbnb New User Bookings competition

python-graph. New official repository: https://github.com/Shoobx/python-graph

keras-resnet. Residual networks implementation using Keras-1.0 functional API

pastalog. Simple, realtime visualization of neural network training performance.

betago. BetaGo: AlphaGo for the masses, live on GitHub.

kaggle-homesite. Top15 Model for Kaggle-Competition "Homesite Quote Conversion"

ensemble_amazon. Code to share different ensemble techniques with focus on meta-stacking , using data from Amazon.com - Employee Access Challenge kaggle competition

Loan_Default_Prediction. This is the Python Code for the submission to Kaggle's Loan Default Prediction by the ID "HelloWorld"

xgbfi. XGBoost Feature Interactions & Importance

keras. Deep Learning for humans