Japanese Input Method System for Linux, Neural Kana-Kanji Conversion Engine + fcitx5 IME

World-Gymnast: Training Robots with Reinforcement Learning in a World Model

Cosmos Policy

AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World | CoRL 2025

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

Damiao Motor Control Library – A Python library for controlling Damiao motors via CAN. Supports Windows, Linux, and macOS. Flexible control modes and real-time motor status feedback. 达妙电机控制库 – 一个用于…

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

スマートファニチャープラットフォーム「カチャカ」API

narabas: Japanese phoneme forced alignment tool

Massive open Japanese speech corpus

Mozc - a Japanese Input Method Editor designed for multi-platform

DayDreamer: World Models for Physical Robot Learning

ChaIME -- Term-based Yet Another Japanese Input Method Editor

Audio Streaming Gateway Suzu

Laser for control mosquito, weed, and pest

Mastering Atari with Discrete World Models

a really basic example of how to do 3-dimensional graphics with Kivy and OpenGL

MediaPipe is a cross-platform framework for building multimodal applied machine learning pipelines

A simple, modern and secure encryption tool (and Go library) with small explicit keys, no config options, and UNIX-style composability.

End-to-End Speech Processing Toolkit

Unofficial Linux driver for PLEX PX4/PX5/PX-MLT series ISDB-T/S receivers (not V4L-DVB)

End-to-End Speech Processing Toolkit

Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations