Chief AI Sharing Circle

General Introduction Vizard, from Blue Pulse, is an online tool that utilizes artificial intelligence technology to help users quickly turn long videos into short social media clips. Designed for content creators, marketers, and educators, it automatically recognizes the best moments in a video and generates short clips for TikTok...

Zeemo, from Blue Pulse, is an AI-based video subtitle generator, focusing on providing video creators with efficient multi-language subtitle solutions. Zeemo automatically recognizes speech in 95 languages and generates subtitles, and translates subtitles into 124 languages....

Comprehensive Introduction Auto-Deep-Research is an open source AI tool developed by the Hong Kong University Data Intelligence Laboratory (HKUDS) to help users automate deep research tasks. It is built on the AutoAgent framework and supports a variety of Large Language Models (LLMs) such as OpenAI, Anthropic, De...

Generalized scenes and vertical scenes, this is the first choice facing the development of AI big models. Currently on the market, most video models are general models, capable of generating video content for various scenarios according to the prompt words input by the user. At the same time, some of the video models have also begun to explore vertical areas that are closer to the application scenarios...

Comprehensive Introduction "Vocabulary Book by DeepSeek" is an open source project developed based on DeepSeek's big model, aiming to help English learners efficiently master the vocabulary of College English IV (CET-4). The project is hosted on GitHub and created by developer vxiaozhi, through Python scripts combined with DeepSe...

Comprehensive Introduction SkyReels is an online platform focused on AI video creation, designed to help users quickly turn text scripts or creative ideas into high-quality short videos. Whether you're a content creator, marketer or a regular user, just type in the text and the platform will automatically generate videos with realistic voice,...

Comprehensive introduction YOLOv12 is an open source project developed by GitHub user sunsmarterjie , focusing on real-time target detection technology . The project is based on YOLO (You Only Look Once) series of frameworks , the introduction of the attention mechanism to optimize the performance of traditional convolutional neural networks (CNN) , not only in the detection of ...

General Introduction AutoAgent is an open source AI intelligences framework developed by the Hong Kong University Data Intelligence Laboratory (HKUDS) and hosted on GitHub.It allows users to rapidly create and deploy customized AI intelligences by describing their requirements in pure natural language, without any programming foundation. The framework supports a wide range of large language...

Comprehensive Introduction Crawl4LLM is an open source project jointly developed by Tsinghua University and Carnegie Mellon University, focusing on optimizing the efficiency of web crawling for pre-training of large models (LLM). It significantly reduces ineffective crawling by intelligently selecting high-quality web page data, claiming to be able to originally need to crawl 100 web pages of work...

General Introduction Deepdive Llama3 From Scratch is an open source project hosted on GitHub that focuses on a step-by-step parsing and implementation of the inference process for Llama3 models. It is optimized based on the naklecha/lllama3-from-scratch project, and is designed to help developers and learners deep...

General Introduction Open-Reasoner-Zero is an open source project focused on reinforcement learning (RL) research, developed by the Open-Reasoner-Zero team on GitHub. It aims to accelerate the research process in the field of artificial intelligence by providing an efficient, scalable and easy-to-use training framework, especially to the pass...

General Introduction Arc Institute Evo 2 is an open source project focused on genome modeling and design, developed by Arc Institute, a non-profit research organization based in Palo Alto, California, and launched in collaboration with partners such as NVIDIA. The project builds, through cutting-edge deep learning techniques,...

Comprehensive Introduction VLM-R1 is an open source visual language modeling project developed by Om AI Lab and hosted on GitHub. The project is based on DeepSeek's R1 approach, combined with the Qwen2.5-VL model, which significantly improves the model's visual... through reinforcement learning (R1) and supervised fine-tuning (SFT) techniques.

Comprehensive Introduction Deep Research Web UI is an open source research assistant tool based on AI technology designed to help users conduct deep iterative research on any topic. It combines the power of search engines, web crawling and large-scale language modeling to provide an efficient research experience through an intuitive web interface. Users ...

General Introduction LiteAvatar is an open source tool developed by the HumanAIGC team (under Ali) that focuses on generating facial animations from audio-driven 2D avatars in real-time. It runs at 30 frames per second (fps) relying only on the CPU, and is especially suited for scenarios that require low power consumption, such as real-time 2D...

General Introduction Botgroup.chat is an open source AI group chat application developed based on React and Cloudflare Pages, aiming to provide users with an interactive experience similar to WeChat group chat. It supports multiple AI characters to participate in conversations at the same time, and users can interact with multiple intelligent bots through a simple configuration...

In the era of information explosion, how to efficiently capture fleeting inspirations and organize fragmented knowledge in an orderly manner, and ultimately transform it into valuable articles and creative materials, has become a common challenge for many content creators and knowledge workers. Recently, a cross-end AI note-taking app called NoteGen has quietly...

Recently, Microsoft Research released a major research result - the basic model of multimodal artificial intelligence agent, Magma. This model can be regarded as a multi-skilled model, which can not only read images and understand language like humans, but also directly operate the user interface (UI) and control robots. It can not only "read" images and "understand" language like a human, but also operate user interfaces (UIs) and control robots directly, which is really eye-catching...