RitoNQ
Follow
Stars
A curated list of awesome papers related to adversarial attacks and defenses for information retrieval. If I missed any papers, feel free to open a PR to include them! And any feedback and contribu…
This repository includes a handout that attempts to outline the entire proof process of the paper written by Cybenko 1989 about the universal approximation theorem of neural networks. The handout c…
a family of versatile and state-of-the-art video tokenizers.
An ultra-lightweight Agentic AI framework based on the ReAct paradigm, supporting mainstream LLMs and is stronger than Swarm.
⚡️充电桩开源云平台⚡️完整源代码，包含模拟桩模块，可通过docker编排快速部署测试。技术栈：SpringCloud、MySQL、Redis、RabbitMQ，前后端管理系统（管理后台、小程序），支持互联互通协议、市政协议、一对多方平台支持。支持高并发业务、业务动态伸缩、桩通信负载均衡（NLB）。
A highly optimized LLM inference acceleration engine for Llama and its variants.
Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.
Modern patch, written in Python. 现代化的 Patch 工具。
Participate in the open source security award program implemented by the China Cyberspace Security Association.
Improving Generalist Model with Domain-Specific Experts
2024年，整理最全面的mysql资料包，含mysql技术文章，paper，面试题，开源项目，电子书
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
🧿 AutorizePro是一款强大越权检测 Burp 插件，通过增加 AI 辅助分析 && 进一步优化检测逻辑，大幅降低误报率，提升越权漏洞检出效率。 [ AutorizePro is a authorization enforcement detection extension for burp suite. By adding Ai-assisted analysis, it sign…
MLCD & UNICOM : Large-Scale Visual Representation Model
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
Honor has a large number of scheduled and periodic tasks that need to be processed on time. Htimer is a microservice system developed in Java, designed to function as an alarm clock service within …
JavaScript Runtime Environment In Embedded Device
The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.
Official implementation of the paper "TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding and Diffusion Interpolation"
以开源为核心的IDaas/IAM平台，用于管理企业内员工账号、权限、身份认证、应用访问，帮助整合部署在本地或云端的内部办公系统、业务系统及三方 SaaS 系统的所有身份，实现一个账号打通所有应用的服务。
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models