#
Starred repositories
The Official Implementation of PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Recipes to train reward model for RLHF.
The "virtual_human_stream" project is a real-time digital human system supporting audio-video dialogue. It integrates models like ernerf, musetalk, and wav2lip for voice cloning, video stitching, a…
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
This is the official reproduction of FancyVideo.
The first open autoregressive foundational video AI model.
⭐ Dynamically generate stats SVG from your Github, LeetCode, Steam, and more in #Cyberpunk style :)
Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
数字底座是一款面向大型政府、企业数字化转型，基于身份认证、组织架构、岗位职务、应用系统、资源角色等功能构建的统一且安全的管理支撑平台。数字底座基于三员管理模式，具备微服务、多租户、容器化和国产化，支持用户利用代码生成器快速构建自己的业务应用，同时可关联诸多成熟且好用的内部生态应用
A Multimodal Native Agent Framework for Smart Hardware and More
EOS is a dual-core operating system designed specifically for embodied intelligence, suitable for robots, drones, satellites or other scenarios requiring real-time and general capabilities.
Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-spee…
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Accelerate your Stable Diffusion inference with the library's universal C/C++ framework design, powered by ONNXRuntime & across platforms.
Next-Generation Interactive Intelligent Programming Assistant
Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine. Empowering millions of developers to create high-performance, engaging 2D/3D gam…
sdlc 是一个基于 Go 语言构建的安全漏洞示范平台，旨在促进 DevSecOps 和安全开发生命周期 (SDLC) 实践。它通过模拟常见漏洞来增强开发人员的安全意识，除了可以用于devsecops以外，还可以用于安全行业从事者学习漏洞知识或者渗透知识，代码审计，提供了一个实践和学习的环境。本项目采用了前后端分离的设计模式，其中后端利用了轻量级框架 Gin，而前端则使用了 Vue 3。
[NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert
cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，支持sso登录，多租户，大数据平台对接，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU，边缘计算，serverless，标注平台，自动化标注，数据集管理，大模型微调，vllm大模型推理，llmops，私有知识库，AI模型应用商店，支持模型一键开发/推理/微调，…
PyTorch Implementation of AudioLCM (ACM-MM'24): a efficient and high-quality text-to-audio generation with latent consistency model.