Github: https://github.com/hkust-nlp/simpleRL-reason This blog will show a replication of DeepSeek-R1-Zero and DeepSeek-R1 training...

General Description Fullmoon is an application designed for iOS devices and aims to provide the ability to chat privately with native large language models. The app is optimized for Apple Silicon and is supported on iPhone, iPad and Mac. Users of the chat...

Model Overview In recent years, large model training based on Mixture of Experts (MoE) architecture has become an important research direction in the field of artificial intelligence.The Qwen team recently released the Qwen2.5-Max model, which uses over 20 trillion to...

General Introduction Onlook is an open source design tool built for designers and developers that allows users to design directly in a running React application and convert design changes to code. The tool provides an intuitive visual editing experience similar to Figma or Webf...

General Introduction YuE is an open source full song generation base model that focuses on transforming lyrics into full songs. Unlike other models that can only generate short snippets of non-vocal music, YuE is capable of generating full songs with lead and backing vocals up to several minutes in length. The model addresses music generation in...

General Introduction PocketPal AI is an open-source mobile app designed to bring Small Language Models (SLMs) directly to your phone for both iOS and Android users...

General Introduction Cog-ComfyUI is an open source project designed to run ComfyUI workflows via an API. Created by GitHub user fofr, the project provides an efficient way to integrate and run ComfyUI workflows.ComfyUI is a ...

General Introduction Supermemory is an open source project designed to help users build their "second brain". With a powerful Chrome extension and AI technology, it allows users to easily save, organize and retrieve data from web pages, Twitter bookmarks,...

General Introduction Open NotebookLM is an open source project designed to convert any PDF document into a podcast. The tool utilizes open source Large Language Model (LLM) and Text-to-Speech (TTS) models to process PDF content and generate natural dialog suitable for audio podcasts...

Comprehensive Introduction Deeptrain is a platform focusing on AI video processing, which is able to effectively integrate video content into various AI applications through its advanced technology that supports over 200 language models. Users can train models directly by providing video URLs without downloading the video...

Comprehensive Introduction Qwen2.5-VL is an open source multimodal big model developed by Qwen team of Alibaba Cloud (Alibaba Cloud). It can handle text, images, video and documents at the same time , is an upgraded version of Qwen2-VL , based on Qwen2.5...

Good New Year! Greetings to all of you! Recently, my circle of friends has been "screened" by news related to DeepSeek-R1, and I believe everyone has heard about our domestic open source model - DeepSeek! I'm sure you've all heard about DeepSeek, our homegrown open source model, and the tutorials on how to deploy DeepSeek-R1 locally have been...

General Introduction Open Intelligence is a company dedicated to providing open source AI solutions, and its main product, Apollo, allows users to interact directly with their private AI backend via their cell phones. The platform not only supports individual users to autonomously manage their AI backends, but also provides...

General Introduction Llamao is a private and offline running Llama AI chatbot designed to provide users with an intelligent assistant service without internet connection. Unlike ChatGPT, Llamao runs entirely on the user's device, ensuring absolute privacy and security of user data. No...

General Introduction Codev is an AI-driven platform designed to help users quickly generate full-stack web applications. Developers and non-developers alike simply describe the application idea through natural language, and Codev generates a complete Next.js with all the necessary components, styles, and features...

I. BACKGROUND AND CHALLENGES With the rapid development of AI technology, large-scale language models (LLMs) have become a core driver in the field of natural language processing. However, training these models requires huge computational resources and time costs, which has led to the rise of Knowledge Distillation (KD) techniques. Knowledge distillation works by ...

General Introduction Lux is a fast and simple video download library and command line tool written in Go. It supports downloading videos from multiple websites, including YouTube, Bilibili, Youku, etc. Lux offers a variety of download options and features, such as multi-threaded download...

General Introduction DeepSeek R1 Overthinker is a tool designed to enhance the depth of thinking of DeepSeek R1 models. By lengthening the model's reasoning process, the tool enables the model to think more deeply, thus improving the quality of its answer...

All Available Courses Include: Basic Introduction + Automation Workflow Hands-on Classes 30 Sessions Basic Classes - Coze Developing Agent Intelligence from Scratch - 54 Sessions https://pan.quark.cn/s/931e5e153f4d#/list/s...

Introduction Like many others, over the past few days my news tweets have been filled with news, praise, complaints, and speculation about the Chinese-made DeepSeek-R1 large language model, which was released last week. The model itself is being brought up against publics like OpenAI, Meta...

DeepSeek has been hit by a large-scale malicious attack that temporarily restricts new registrations due to an attack on its online service that has resulted in a busy registration process. The issue started to erupt around January 27, 2025 by a deepseek api error report, during which registration also experienced small-scale issues...

Summary of the main contributions of CORAG CORAG (Cost-Constrained Retrieval Optimization for Retrieval-Augmented Generation) is a...

Comprehensive Introduction FloatSearch AI is a cross-language intelligent search engine based on artificial intelligence technology, designed to provide users with a more accurate and efficient search experience. It understands users' natural language queries and provides relevant and accurate answers based on semantic analysis.FloatS...

Knowledge distillation is a machine learning technique that aims to transfer learning from a large pre-trained model (i.e., a "teacher model") to a smaller "student model". Distillation techniques can help us develop lighter weight generative models for intelligent conversations, content creation, and other domains. Recently ...

Comprehensive Introduction LangbaseInc's Langui is an open source user interface component library designed for generative AI and Large Language Model (LLM) projects. The library is based on Tailwind CSS and provides a collection of pre-built UI components to help developers quickly construct...

1.Introduction to the Model In the five months since the release of Qwen2-VL, numerous developers have built new models on top of the Qwen2-VL visual language model, providing valuable feedback to the Qwen team. During this time, the Qwen team has focused on building more useful visual language models...

Recently, many people engaged in large model training and reasoning have been discussing the relationship between the number of model parameters and model size. For example, the famous alpaca series LLaMA large model contains LLaMA-7B, LLaMA-13B, LLaMA-33B and LLaMA...

JanusFlow Quick Reads The DeepSeek team is back with a new model, launching in the early hours of the 28th morning the innovative multimodal framework Janus-Pro, a unified model that can handle both multimodal comprehension and generation tasks. The model is based on the DeepSeek-LLM...

Toward the end of the year, the domestic large modeling field is again spreading good news. Baichuan Intelligence recently intensively released a number of large model products, following the full-scene deep inference model Baichuan-M1-preview and medical augmented open source model Baichuan-M1-14B, and then re-launched the full-modal...

General Description Your Daily Minute is an innovative video diary app that uses AI technology to help users record and understand daily emotions. Users can record a one-minute video reflection each day, and the app automatically transcribes and analyzes the emotional content to provide instant insight into their emotional state. The ...

General Description Taskek is an AI-driven productivity tool with integrated Trello, Google Docs and Miro functionality for all types of work environments, from high-rise buildings to home offices. It allows teams to start with simple drawings and quickly translate them into specific tasks, raising...

Comprehensive Introduction MNN (Mobile Neural Network) is an efficient, lightweight deep learning framework developed by Alibaba and optimized for mobile devices.MNN is not only capable of fast inference on mobile devices, but also supports multimodal tasks, including text generation...

General Introduction LearnGerman.ai is an online platform focused on learning German, offering personalized German lessons and free resources. Whether you are a beginner or an advanced learner, LearnGerman.ai offers customized lessons tailored to your level and learning progress...

General Introduction AI RSS is an innovative tool that converts web content into RSS feeds through AI technology. It consists of two main parts: a browser plugin and a server side. The browser plugin allows users to select lists from web pages and generate structured data description (SDD) files...

Today, DeepSeek, a rising star in China's AI field, has triggered an "earthquake" in the global science and technology industry with its amazing speed and strength. This application, which is known as "the light of domestic AI", not only pushed ChatG...

Comprehensive Introduction UltraRAG is a RAG (Retrieval Augmented Generation) system solution jointly proposed by the THUNLP group at Tsinghua University, the NEUIR group at Northeastern University, Modelbest.Inc and the 9#AISoft team. The framework is based on agile deployment and modularized building...

General Description AI Company Research Assistant is an artificial intelligence-based tool designed to automate the company research and lead generation process. By using technologies such as LangGraph and FireCrawl, the tool is able to generate detailed company research reports in just a few minutes. Users simply need to...

General Introduction Adam CAD is an intelligent tool that utilizes artificial intelligence technology to generate CAD designs. Users can quickly generate CAD files for a variety of mechanical and industrial designs using natural language input. Whether it's designing a Raspberry Pi enclosure with vents and IO ports, or creating a...

General Introduction SemajAI is an artificial intelligence assistant designed for learning Japanese. By having a conversation with the AI assistant, users can learn and master Japanese speaking and listening in 100 days.SemajAI provides rich vocabulary and phrases to help users practice each topic in...

In late 2024, YC Partner Jared predicts that vertical AI Agents will be an emerging market 10x larger than SaaS in the next few years, and that the space could also spawn tech giants with market caps of over $300 billion. By then, Microsoft CEO Saty...

General Description InboxPilot is an AI email automation tool designed for businesses to intelligently compose and send email responses by utilizing internal company data. It not only saves time but also improves the efficiency and quality of customer service. The tool is especially suited to handle large amounts of support...

Based on the first two generations of video models (CogVLM2-Video and GLM-4V-PLUS), we have further optimized our video understanding techniques with the release of the GLM-4V-Plus-0111 beta version. This version introduces techniques such as native variable resolution to improve ...

General Introduction HyperUGC is an innovative platform that utilizes artificial intelligence technology to generate high-quality user-generated content (UGC) videos. The platform is designed to replace expensive content creators by generating authentic and engaging video content in minutes through AI avatars.Hype...

General Introduction KlipML is an advanced AI video creation platform designed to help users quickly generate professional videos. Whether it's marketing content, educational videos or social media clips, KlipML simplifies the video production process with its powerful AI capabilities. The platform offers AI agent...

General Description Wepost is a content marketing platform designed for busy marketers that utilizes artificial intelligence technology to help users create high-quality branded content. The platform integrates content planning, creation, publishing and analytics features designed to streamline workflows and increase the efficiency of content marketing. Users...

General Introduction Llasa-3B is an open source text-to-speech (TTS) model developed by the Audio Lab of the Hong Kong University of Science and Technology (HKUST Audio). The model is based on the Llama 3.2B architecture, which has been carefully tuned to provide high-quality speech generation that not only supports multiple...

Comprehensive Introduction Fast GraphRAG is an open source tool developed by Circlemind AI to enable efficient and accurate retrieval augmentation generation (RAG) through knowledge graph and PageRank algorithms. The tool intelligently adapts to the user's use...

A First Look at MCP MCP (Model Context Protocol), is a protocol developed to standardize how applications provide context for large models.MCP provides a standard way of providing data, tools for LLMs.Using MCP will make it easier to con...

1. Introduction Two months ago, the Qwen team upgraded Qwen2.5-Turbo to support context lengths of up to one million Tokens. Today, Qwen officially launched the open source Qwen2.5-1M model and its corresponding inference framework support. The following...

2025 the beginning of the year, the AI industry set off a large model "reasoning tide", since OpenAI released o1, various reasoning models continue to emerge, the model's higher-order reasoning ability ushered in the outbreak of enhancement of the value of its application is also more and more to obtain the industry's widespread attention. Recently, NetEase has officially launched the first domestic output step-by-step...

General Introduction TinyZero is a veRL-based reinforcement learning model designed to replicate the performance of DeepSeeK-R1 Zero in countdown and multiplication tasks. Surprisingly, the project costs only $30 to run (using 2xH2...

General Introduction Hugging Face's Open R1 project is a fully open-source DeepSeek-R1 replication project designed to build the missing parts of the R1 pipeline so that everyone can replicate and build upon them. The project is designed to be simple and consists mainly of training and evaluating...

The cue word is derived from the AI programming tool CodeGuide, which utilizes this cue word and the latest Deepseek-R1 model to achieve an o1-like response effect, replacing the o1 thought process and reducing the overall API cost by 50%. The cue word tech...

Tip Please perform a comprehensive security audit of the Cerebr-main browser extension, including an...

General Introduction Open Operator is an open source project that aims to automate operations in the browser through AI intelligences. Developed by Browserbase, the project combines the technologies of Stagehand and Browserbase...

General Description Cerebr is a powerful AI assistant extension for Chrome, designed to enhance your productivity and learning experience.Cerebr was designed from the ground up with the need for a clean, efficient browser AI assistant, with a minimalist design and powerful...

General Introduction TubeTube is an open source YouTube video download tool developed by MattBlackOnly. The tool uses yt-dlp as the core download engine, supports multi-threaded downloads, and is able to quickly download multiple videos at the same time. Users can yam...

Comprehensive Introduction LangWatch is a comprehensive platform designed for Large Language Model (LLM) operations, providing monitoring, analysis, evaluation, dataset management, and cue optimization. The platform is based on Stanford University's DSPy framework and is designed to help users better manage and optimize...

1. Introduction: A New Era of Image Generation In today's digital age, image generation technology has made impressive strides. Whether you are a designer, an artist, or just a regular person who wants to create personalized content, image generation tools can help bring your ideas to life. However, traditional image...

General Introduction PR-Agent is an open source tool developed by Qodo to automate the processing of pull requests (Pull Requests) through AI technology. The tool is able to provide automated feedback, suggestions, and analytics to help developers perform code reviews more efficiently...

Where did the PR Assistant come from? PR Assistant is a new player in the software development arena. It came about because people needed to make it easier to manage code changes. It came about because of the need to make it easier to manage code changes, which used to be a pain in the ass for people to do. PR Assistant started as a way to automate simple checks, but has become very...

Comprehensive Introduction FinGPT is an open source financial big language modeling platform developed by the AI4Finance Foundation, designed for the financial sector to solve complex financial tasks and drive innovation in fintech.FinGPT utilizes lightweight adaptation techniques and reinforcement learning approaches...

On the same day that Cline released the Plan & Act model, DeepSeek introduced the R1 model. An interesting phenomenon ensued: developers started spontaneously using R1 for the planning phase, while using 3.5-Sonnet...

Recently Cursor started to block the account, the client will appear prompt Unauthorized request, User is unauthorized Pro account in trying to switch Enable usage-based pric...

General Introduction Coding Agent is an intelligent programming assistant developed by AbhinavTheDev, designed to help developers improve their programming efficiency. The tool utilizes artificial intelligence technology to automatically generate code, provide programming suggestions, and assist developers with various coding...

Comprehensive Introduction Kluster.ai is an AI inference platform designed for developers to provide efficient and cost-effective large-scale AI processing solutions. The platform dynamically adjusts computational resources to ensure efficient batch and real-time processing capabilities through adaptive inference technology.Klust...

General Introduction Hyperbolic is an AI cloud platform dedicated to providing open access to affordable GPU access and inference services for edge AI users. Whether you are a researcher, an enterprise or a startup, Hyperbolic offers a wide selection of GPUs through its...

Original article: https://arxiv.org/pdf/2412.15479 Interpretation: this article itself is not very innovative and has little application. However, it reminds me of three highly informative articles I read a long, long time ago, and reading this article in conjunction with the three previous ones will hopefully give...

Comprehensive Introduction Ragas is a tool specifically designed to evaluate and optimize Retrieval Augmented Generation (RAG) systems. It provides a comprehensive set of evaluation metrics by analyzing the relationships between queries, retrieval contexts, and generated answers. These metrics include fidelity, answer relevance, context relevance, on...

Comprehensive Introduction VeighNa is a Python-based open source quantitative trading platform originally developed by domestic private traders and officially launched in 2015. It has evolved from a simple trading interface package to a full-featured trading development framework. Users include private equity funds, certificates...

General Introduction OpenCharacter is an open source character creation tool designed to provide users with an unfiltered and unlimited AI character creation and interaction experience as a Character.AI alternative. Users can create and run their own characters using native models, or...

General Introduction Video Starter Kit (Video Starter Kit) is an open source project released by fal-ai-community to show how to utilize AI models for video production in the browser. It provides tools to convert from image to video...

General Introduction Text2Edit is an open source project , hosted on GitHub , aims to provide efficient text editing and advertisement generation functions . The main goal of the project is to help users quickly process text content and generate high-quality ads through an easy-to-use interface and powerful ...

General Introduction ChatWise is a high-performance AI chatbot that supports a wide range of Large Language Models (LLMs), including GPT-4, Claude, and Gemini.ChatWise focuses on user privacy, with all data stored locally on the device, ensuring that users...

General Introduction SkyPilot is an open source framework initiated by the Sky Computing Lab at the University of California, Berkeley, designed to help users efficiently run AI and batch processing tasks on any cloud infrastructure. It supports over 14 cloud services (including ...

General Introduction LlamaEdge is an open source project designed to simplify the process of running and fine-tuning large language models (LLMs) on local or edge devices. The project supports the Llama2 family of models and provides OpenAI-compatible API services that enable users to easily create and run...

Day of AI (Artificial Intelligence Day) was born in June 2021 at MIT. Led by a team of faculty and research scientists from MIT's RAISE (Responsible Artificial Intelligence and Education), the Day of AI program aims to do for students of all backgrounds and abilities...

Comprehensive Introduction AutoGen is an open source framework developed by a team of Microsoft researchers focused on simplifying the building of large language model (LLM) applications through multi-intelligent body conversations. It allows developers to create AI agents that can talk to each other and collaborate to solve tasks. This approach not only improves the performance of LLM...

In the field of artificial intelligence and machine learning, especially when building applications such as RAG (Retrieval Augmented Generation) systems and semantic search, efficiently processing and retrieving massive unstructured data becomes crucial. Vector databases have emerged as a core technology to address this challenge. They are not only for storing high-dimensional ...

General Introduction aiCoder is a tool that utilizes artificial intelligence techniques to simplify JavaScript library development. It helps developers save time and improve code quality through intelligent code suggestions and automated code merging. aiCoder is unique in its use of abstract syntax trees...

In today's rapidly changing technology, artificial intelligence (AI), as a force to be reckoned with, is profoundly changing the way we live and work. And in the surging wave of AI, Ten Square Ronghai Xiaozhi AI Voice Box has jumped to the top of GitHub with its excellent performance and innovative user experience...

Xiaohongshu, a hot social e-commerce platform in China and even in Asia, has long gone beyond a simple shopping app to become a weathervane for young people's lifestyles and a new position for brand marketing. For overseas brands and individuals wishing to enter the Chinese market or reach young consumers, mastering Xiaohongshu...

Unexpectedly, AI has set off a half-changing sky in the programming field. From v0, bolt.new to various programming tools Cursor and Windsurf that combine Agant, AI Coding has a huge potential of idea MVP. From...

Comprehensive Introduction LiveKit is an open source project focused on helping developers build real-time audio and video applications. It is based on WebRTC technology , provides a complete solution , including media servers and a variety of client SDKs.LiveKit's core is an extensible ...

General Introduction Page Assist is an open source browser extension designed to provide users with an easy way to interact with local AI models. With this extension, users can open a sidebar on any web page to interact with locally running AI models.Page Assi...

General Introduction Decagon is a company focused on providing enterprise-grade generative AI customer support solutions. Its core product is intelligent AI customer service intelligences that are capable of handling complex issues, integrating seamlessly with existing systems, and learning continuously from data.Decagon's solutions are designed to...

General Introduction MobileAgent is a powerful mobile device operation assistant designed to improve the efficiency and automation of mobile device operation through multi-agent collaboration and enhanced visual perception modules. It is developed by X-PLUG team and supports Android and ...

Original article: https://cdn.openai.com/operator_system_card.pdf UNDERSTANDING: OpenAI Launches Operator, the First L3-Level Intelligence: Opening a New Era of Human-Computer Interaction 1 INTRODUCTION Ope...

The Computer Use track is crowded with startups and dark horses, as well as giant bigwigs, and now OpenAI is killing it. You can follow Desktop Automation Intelligentsia , we collected dozens of related products. The artificial intelligence field is becoming increasingly competitive, with not only startup newcomers emerging...

General Introduction Orama is an open source, high-performance search engine , written entirely in TypeScript , supporting full-text search , vector search and hybrid search.Orama is designed to work in any JavaScript runtime environment , providing fast , reliable ...

Thanks to Tencent Cloud Cloud Studio, thanks to DeepSeek DeepSeek-R1 In today's world of rapid development of artificial intelligence and big model technology, more and more developers and researchers want to experience and fine-tune big models for themselves in order to better understand and apply these advanced techniques...

OpenAI has set its sights on the life sciences this time around, partnering with Retro Biosciences, a company dedicated to extending lifespan, to launch a new AI model, the GPT-4b Micro. This groundbreaking technology may reshape the rules of protein design, with the goal of...

General Introduction FramePainter is a revolutionary AI-driven image editing tool that utilizes advanced video diffusion technology and intuitive Sketch controls to help users easily achieve complex image editing. Whether it's a simple adjustment or a complex creative transformation, Fr...

Synthesis Gaze-LLE is a gaze target prediction tool based on a large-scale learning encoder. It was developed by Fiona Ryan, Ajay Bati, Sangmin Lee, Daniel Bolya, Judy Hoffman, and J...

Most of the intelligences we developed in the past were in a fixed workflow mode, and very few of them followed the framework below to develop intelligences with autonomous decision making and autonomous use of tools. Two days ago, I shared browse, an open source Agent that can automate simple tasks using a browser...

Today I want to share a true and exciting cold start story, and here's what happened: I was lurking around on tubes the other day and swiped on a video by software review blogger LearnWire: "THIS NEW AI Tool CRUSHES Lovable For...

General Introduction Fey is an intelligent assistant designed for modern investors, providing real-time market data and personalized investment advice. With a simple and intuitive interface, users can easily access important financial information and market trends.Fey's core features include stock tracking, financial analysis, personalized new...

General Introduction Needle is an artificial intelligence platform designed for enterprises to enhance their productivity through efficient information search and automated workflows. The platform is capable of connecting various data sources within an organization to provide unified search and data management capabilities. Users can simply...

General Introduction Rapport Cloud is a cloud-based platform focused on creating and deploying interactive digital characters powered by artificial intelligence. Developed by the Speech Graphics team, the platform utilizes its award-winning audio-driven facial animation technology, widely used in AAA...