A Conversational Speech Generation Model

Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

docker-registry proxy run in cloudflare workers

Reverse Engineering: Decompiling Binary Code with Large Language Models

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

🎤⌨️ Acoustic keyboard eavesdropping

Pitch / fundamental frequency detection library for C,C++,C#

Run macOS VM in a Docker! Run near native OSX-KVM in Docker! X11 Forwarding! CI/CD for OS X Security Research! Docker mac Containers.

Open source ultrasound processing modules and building blocks

Imaging ultrasound dev/hacking kit

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

computer vision and sports

Collection of Free English/Chinese Fonts for Commercial Use. 收录可商用的免费英文/汉字字体。

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

Multilingual Voice Understanding Model

llama3 implementation one matrix multiplication at a time

Continuation of Il2CppInspector - A powerful automated tool for reverse engineering Unity IL2CPP binaries.

Decompilation/Dissasemble of Harvest Moon for SNES

Llama3、Llama3.1 中文后训练版仓库（微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

Check out the new game server:

Football game

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.