A Speech-to-Text Input Method For Windows

Engy is an AI-powered development tool that generates fully functional web applications from natural language, streamlining the process from idea to working prototype.

PyTorch Implementation of StyleSinger(AAAI 2024): Style Transfer for Out-of-Domain Singing Voice Synthesis

Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning

Abracadabra 魔曰，下一代文本脱敏和加密工具

Efficient DiT architecture for text2any tasks, ICLR2025

deploy yolov5 and yolov8 with python, c++ and rust

Nestjs project, Reactjs project, Full stack project, project for beginner, Access Control System, Authorization Management System

This project uses yolov8 combined with bytetrack to achieve multi-target tracking

The first open autoregressive foundational video AI model.

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

One-stop data intelligence agent, providing insights from all mainstream data formats in a single dialogue box, including documents, databases, business systems, and images.一站式数据智能体，一个对话框提供所有主流格式数据…

Just Ceal It (可用于无代理合法抵御网络监听和开展网络研究)

工作流引擎对内提供单位/机关流程管理规则和内部业务流程的数字化落地实践；对外提供自动化地第三方业务驱动、接口接入和算法单元驱动能力。工作流引擎在提供底层驱动引擎的同时对全局透明监控、安全防御和国产化特色功能进行充分考虑，是内部流程管理和业务算法驱动的不二之选。

(ECCV 2024) Empowering Multimodal Large Language Model as a Powerful Data Generator

Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

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…

MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes; NeurIPS 2024; Official code

数据标注是一款专门对文本数据进行处理和标注的工具，通过简化快捷的文本标注流程和动态的算法反馈，支持用户快速标注关键词并能通过算法持续减少人工标注的成本和时间。数据标注的过程先由人工标注构建基础，再由自动标注反哺人工标注，最后由人工标注进行纠偏，从而大幅度提高标注的精准度和高效性。数据标注需要依赖开源的数字底座进行人员岗位管控。

AI外呼系统，基于自然语言处理（NLP）、语音识别（ASR）、语音合成（TTS）和通讯（freeswitch）技术，实现自动语音应答，听说状态的实时切换，用自然逼真的对话与客户沟通。

[arXiv 2024] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".

2d game, a birthday present for my girl friend, the game prototype is Magic Tower

数据流引擎是一款面向数据集成、数据同步、数据交换、数据共享、任务配置、任务调度的底层数据驱动引擎。数据流引擎采用管执分离、多流层、插件库等体系应对大规模数据任务、数据高频上报、数据高频采集、异构数据兼容的实际数据问题。

Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility.

High performance minimalism async-io(proactor) networking for Golang.

[ICLR 2025] MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

A project that uses a web page to showcase outbreaks in the United States.

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、数据目录、安全控制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。