[{"data":1,"prerenderedAt":378},["ShallowReactive",2],{"$fgukOamtKU1RtUiMFsqdObttmqPPQz0uc7bl_gj_LyX0":3,"$fAbhxtVImRaZXMCeD8adNy0f4kONr4Zwl--vgr9gGHsg":245,"article-197":377},{"code":4,"msg":5,"data":6},0,"",{"category":7,"tag":11,"popular":19,"latest":86,"banner":126,"list":151,"cache":244},[8,9,10],"Agent","OpenAI","LLM",[8,12,13,14,9,10,15,16,17,18],"Google","Nvidia","Claude","DeepSeek","OCR","Chat","Generator",[20,29,37,45,54,62,70,79],{"id":21,"publish_date":22,"is_original":23,"collection":5,"cover_url":24,"cover_url_1_1":25,"title":26,"summary":27,"author":28},411,"2023-09-10",1,"article_res/cover/451ef50c225a8dc61c4336506794d13b.jpeg","article_res/cover/3ba9dc7a72f87d40b20fc2d225289ee3.jpeg","Idealism","Reality is created by the mind, we can change our reality by changing our mind. - Plato","Renee's Entrepreneurial Journey",{"id":30,"publish_date":31,"is_original":23,"collection":32,"cover_url":33,"cover_url_1_1":34,"title":35,"summary":36,"author":28},108,"2024-12-07","#LLM #AGI #AI Agent","article_res/cover/0039044422e4ec9f61c18e8ee1693bb0.jpeg","article_res/cover/4220971b108a91d21407d87bb02fbaa6.jpeg","Freysa.ai: The World's First Adversarial AI Agent Game","说服 Freysa 把钱包里的钱都拿出来",{"id":38,"publish_date":39,"is_original":23,"collection":40,"cover_url":41,"cover_url_1_1":42,"title":43,"summary":44,"author":28},12,"2025-03-09","#Oxford #Reasoning #LLM #Tool Use","article_res/cover/d448e9b3617a0b5302e1bd10c438bca9.jpeg","article_res/cover/864a468f9cc4c9317efadb3811909888.jpeg","Agentic Reasoning Framework - Significantly enhance the reasoning ability of LLMs through the integration of external tools using agents","Agentic Reasoning: Reasoning LLMs with Tools for Deep Research",{"id":46,"publish_date":47,"is_original":4,"collection":48,"cover_url":49,"cover_url_1_1":50,"title":51,"summary":52,"author":53},480,"2023-04-14","#Stable Diffusion","article_res/cover/0bdbe7cb1de4a78e54536e5d9afa7ec9.jpeg","article_res/cover/b3d6ffec0608dcfaf18c5a69906d1490.jpeg","【AIGC Learning】Generate Prompts Using Word Graphs - Stable Diffusion Web UI Series 13","AI will become a powerful tool in education, transforming the way we learn and deliver instruction.  \n- Reid Hoffman","--",{"id":55,"publish_date":56,"is_original":4,"collection":57,"cover_url":58,"cover_url_1_1":59,"title":60,"summary":61,"author":28},413,"2023-09-08","#Neuroscience","article_res/cover/74f8302d78a23d9430f22171eae136b6.jpeg","article_res/cover/87ca08af81bb304746be5261160964c0.jpeg","Can machines be conscious?","Do we have an ethical obligation to not turn off conscious machines? Would turning them off be murder? No. I don't lose any sleep over unplugging a conscious machine.\n- Jeff Hawkins, \"A Thousand Brains\"",{"id":63,"publish_date":64,"is_original":23,"collection":65,"cover_url":66,"cover_url_1_1":67,"title":68,"summary":69,"author":28},178,"2024-09-09","#Entrepreneurship","article_res/cover/a7224f025b55d1820408085faef63079.jpeg","article_res/cover/11a9995b096cbf64465ef01b8673b154.jpeg","37signals company","This damn sense of relaxation",{"id":71,"publish_date":72,"is_original":4,"collection":73,"cover_url":74,"cover_url_1_1":75,"title":76,"summary":77,"author":78},460,"2023-05-12","#Google","article_res/cover/b970687b12faa52da976f91248c2aa7b.jpeg","article_res/cover/d1e71b52cfd2c63bc6e71f3e85ff135c.jpeg","Learn what BRC-20 and Ordinals are using Google Bard","Ordinals - a new protocol that allows users to store arbitrary data on the Bitcoin blockchain","Google Bard mainly writes",{"id":80,"publish_date":81,"is_original":23,"collection":5,"cover_url":82,"cover_url_1_1":83,"title":84,"summary":85,"author":28},309,"2024-03-26","article_res/cover/9877f95894ee88532d0e6012c23a2df3.jpeg","article_res/cover/20092164ddc109ce6ae56b1984246751.jpeg","Learning the Cancun Upgrade with lepton and perplexity","Building a quick conversation-based search demo with Lepton AI.",[87,95,103,111,119],{"id":88,"publish_date":89,"is_original":23,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":28},627,"2025-03-20","#AI Avatar #AI Video Generation","article_res/cover/d95481358f73924989f8c4ee9c75d1c8.jpeg","article_res/cover/b74bc0fab01f8b6a6aa87696c0c3ed8b.jpeg","DisPose: Generating Animated Videos by Driving Video with Reference Images","DisPose is a controllable human image animation method that enhances video generation.",{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},626,"2025-03-21","#Deep Dive into LLMs #LLM #RL #Andrej Karpathy #AlphaGo","article_res/cover/446553a5c8f8f2f07d97b20eaee84e56.jpeg","article_res/cover/e6c2823409c9b34624064b9acbaca6f1.jpeg","AlphaGo and the Power of Reinforcement Learning - Andrej Karpathy's Deep Dive on LLMs (Part 9)","Simply learning from humans will never surpass human capabilities.",{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},625,"2025-03-22","#Deep Dive into LLMs #LLM #RL #RLHF #Andrej Karpathy","article_res/cover/8da81d38b1e5cf558a164710fd8a5389.jpeg","article_res/cover/96f028d76c362a99a0dd56389e8f7a9b.jpeg","Reinforcement Learning from Human Feedback (RLHF) - Andrej Karpathy's Deep Dive on LLMs (Part 10)","Fine-Tuning Language Models from Human Preferences",{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},624,"2025-03-23","#Deep Dive into LLMs #LLM #Andrej Karpathy #AI Agent #MMM","article_res/cover/a5e7c3d48bb09109684d6513287c661d.jpeg","article_res/cover/d3f22b7c0ab8d82fd2da457a299e0773.jpeg","The Future of Large Language Models - Andrej Karpathy's In-Depth Explanation of LLM (Part 11)","preview of things to come",{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},623,"#Google #Voe #AI Video Generation","article_res/cover/c44062fea0f336c2b96b3928292392c2.jpeg","article_res/cover/a041041c69092ad3db191c5bf3ff981b.jpeg","Trial of Google's video generation model VOE2","Our state-of-the-art video generation model",[127,135,143],{"id":128,"publish_date":129,"is_original":23,"collection":130,"cover_url":131,"cover_url_1_1":132,"title":133,"summary":134,"author":28},300,"2024-04-16","#AI in Science #AGI","article_res/cover/6bf01e793e0f33e848572412eebdf9b0.jpeg","article_res/cover/91a5ee21dafecb914fabeb9430d46ec1.jpeg","Would Einstein lose his job - AI and Quantum Computing: A Glimpse into the Near Future","So Einstein's job is still safe.",{"id":136,"publish_date":137,"is_original":23,"collection":138,"cover_url":139,"cover_url_1_1":140,"title":141,"summary":142,"author":28},101,"2024-12-14","#Nvidia #AI 3D Generator","article_res/cover/693e07c85980c5c0c8fde3f037733f23.jpeg","article_res/cover/9ea8edff2d5d303ff3fffff3f6f9c3d9.jpeg","NVIDIA's open-source 3D project LLaMA-Mesh","LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models",{"id":144,"publish_date":145,"is_original":23,"collection":146,"cover_url":147,"cover_url_1_1":148,"title":149,"summary":150,"author":28},131,"2024-11-10","#OpenAI","article_res/cover/87f8ed353ce39f31960e7cdfaf075a35.jpeg","article_res/cover/f597a63935f5cd32e484b4aadd6019e8.jpeg","ChatGPT has launched the Search function","Get fast, timely answers with links to relevant web sources.",{"big":152,"small":214},[153,181],{"title":154,"list":155},"AGENT",[156,157,165,173],{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":158,"publish_date":159,"is_original":23,"collection":160,"cover_url":161,"cover_url_1_1":162,"title":163,"summary":164,"author":28},622,"2025-03-24","#OWL #AI Agent #MAS #MCP #CUA","article_res/cover/cb50ca7f2bf4d1ed50202d7406e1c19a.jpeg","article_res/cover/4aa7aa3badfacf3cc84121334f1050dd.jpeg","OWL: Multi-agent collaboration","OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation",{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},620,"2025-03-26","#LLM #Google #Gemini #AI Agent","article_res/cover/53751a6dbbe990b1eb0b63f3b062aed4.jpeg","article_res/cover/031344981f0a212ff82d1f3a64aa5756.jpeg","Gemini 2.5 Pro, claimed to be far ahead of the competition, has been released with great fanfare: comprehensively surpassing other LLMs and topping the global rankings","Gemini 2.5: Our most intelligent AI model",{"id":174,"publish_date":175,"is_original":23,"collection":176,"cover_url":177,"cover_url_1_1":178,"title":179,"summary":180,"author":28},616,"2025-03-29","#MAS #AI Agent #AI Coder #MetaGPT #MGX","article_res/cover/9dcd702ad2035902e5e77967c34a1f1e.jpeg","article_res/cover/0a97fc4a922753c8f46ff38792020df8.jpeg","MGX - An automated website-building platform composed of multiple AI Agents","Your 24/7 AI Team | Dream, Chat, Create.",{"title":182,"list":183},"OPENAI",[184,191,199,206],{"id":185,"publish_date":167,"is_original":23,"collection":186,"cover_url":187,"cover_url_1_1":188,"title":189,"summary":190,"author":28},619,"#OpenAI #AI Image Generator #4o #MMM #AR Transformer","article_res/cover/2faffc97fcecf3151552cb0fd3206d89.jpeg","article_res/cover/1133cb4948af44cee2e7fbe79efb69e5.jpeg","The native image function of GPT-4o is officially launched","Introducing 4o Image Generation",{"id":192,"publish_date":193,"is_original":4,"collection":194,"cover_url":195,"cover_url_1_1":196,"title":197,"summary":198,"author":28},434,"2023-07-15","#Anthropic #OpenAI #Google #AI Code Generator #Claude","article_res/cover/e1b6f600a2b9f262a4392684e5f2ce25.jpeg","article_res/cover/6e1772e83f78f9a351ab23d3e414adee.jpeg","Latest Updates on Google Bard /Anthropic Claude2 / ChatGPT Code Interpreter","We want our models to use their programming skills to provide more natural interfaces to the basic functions of our computers.  \n - OpenAI",{"id":200,"publish_date":201,"is_original":4,"collection":146,"cover_url":202,"cover_url_1_1":203,"title":204,"summary":205,"author":28},417,"2023-08-24","article_res/cover/bccf897d50a88b18364e35f7466387e0.jpeg","article_res/cover/2f871085c1073717c1703ae86e18056f.jpeg","The GPT-3.5 Turbo fine-tuning (fine-tuning function) has been released～","Developers can now bring their own data to customize GPT-3.5 Turbo for their use cases.",{"id":207,"publish_date":208,"is_original":4,"collection":209,"cover_url":210,"cover_url_1_1":211,"title":212,"summary":213,"author":28},407,"2023-09-22","#OpenAI #AI Image Generator","article_res/cover/c59005e903d35cfc32346e2756e2728a.jpeg","article_res/cover/ba011d265e6d84b5c8cb6fd6b757b6cc.jpeg","Dall-E 3","DALL·E 3 understands significantly more nuance and detail, allowing you to easily translate your ideas into images.",[215,221,241],{"title":10,"list":216},[217,218,219,220],{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"title":222,"list":223},"GOOGLE",[224,225,226,234],{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"id":227,"publish_date":228,"is_original":23,"collection":229,"cover_url":230,"cover_url_1_1":231,"title":232,"summary":233,"author":28},615,"2025-03-30","#AI Researcher #AI Science #HKU #Google #AI Agent","article_res/cover/21fadf906067714bb0db31ae13a77c15.jpeg","article_res/cover/2697999a72bd26b22e85f0e92936d3ed.jpeg","AI-Researcher: LLM-driven全自动 scientific research assistant","AI-Researcher: Fully-Automated Scientific Discovery with LLM Agents  \nOpen-Sourced Alternative to Google AI Co-Scientist",{"id":235,"publish_date":236,"is_original":23,"collection":73,"cover_url":237,"cover_url_1_1":238,"title":239,"summary":240,"author":28},463,"2023-05-09","article_res/cover/89800f207723acdb55fc53bf999ebdc9.jpeg","article_res/cover/5764f369b4accd8f83e94aa4c077a175.jpeg","The Smallville sandbox world - A town with 25 virtual residents","Believable proxies of human behavior can empower interactive apps: Immersive environment, Rehearsal space, Prototyping tool",{"title":242,"list":243},"NVIDIA",[],true,{"code":4,"msg":5,"data":246},{"id":247,"publish_date":248,"is_original":23,"collection":5,"articles_id":249,"cover_url":250,"cover_url_1_1":251,"title":252,"summary":253,"author":28,"content":254,"popular":255,"list":320,"category":375,"tag":376},197,"2024-08-14","p_7E7Ycky9bKRuRl3TTDQQ","article_res/cover/22174743c1501f73c6b18fe0c76eaba5.jpeg","article_res/cover/a4056722ad71dc449138929b900a70fd.jpeg","MiniCPM, a GPT-4V-level multimodal language model running on mobile devices","Today I studied a project called MiniCPM, which is a GPT-4V-level multimodal language model (MLL) running on mobile phones.","\u003Cdiv class=\"rich_media_content js_underline_content\n                       autoTypeSetting24psection\n            \" id=\"js_content\">\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>Today I studied a project called MiniCPM, which is a GPT-4V-level multimodal language model (MLLM) that runs on mobile devices and supports the processing of single images, multiple images, and videos.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006245\" data-ratio=\"0.7138888888888889\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802868220.0931815780561962.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>It is a series of edge-side multimodal language models designed for visual-language understanding. These models can take images, videos, and text as input and generate high-quality text output. Since February 2024, five versions have been released with the goal of achieving strong performance and efficient deployment.\u003C/p>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);cursor: pointer;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\"cursor: pointer;font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Version 2.6 update\u003C/span>\u003C/h2>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>: 🔥🔥🔥 This is the latest and most powerful model in the MiniCPM-V series. The model has 8 billion parameters and surpasses GPT-4V in single-image, multi-image, and video understanding. It outperforms GPT-4o mini, Gemini 1.5 Pro, and Claude 3.5 Sonnet in single-image understanding, and exceeds MiniCPM-Llama3-V 2.5 in OCR capability, reliability, multilingual support, and edge-side deployment. Due to its excellent token density, MiniCPM-V 2.6 has achieved real-time video understanding capabilities on edge-side devices such as iPads for the first time.\u003C/p>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423802866600.5789233575988939.mp4\" poster=\"./assets/17423802866660.22175766183878776.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);cursor: pointer;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\"cursor: pointer;font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Examples\u003C/span>\u003Cspan style=\"cursor: pointer;font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;text-align: left;\">\u003Cp style=\"text-align: center;\">\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>Example 1\u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>: \u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>Bicycle\u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>Repair techniques\u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003C/span>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006251\" data-ratio=\"2.3074074074074074\" data-s=\"300,640\" data-type=\"png\" data-w=\"540\" style=\"letter-spacing: 0em;\" src=\"./assets/17423802869780.957671918526996.png\">\u003Cbr>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006252\" data-ratio=\"2.3\" data-s=\"300,640\" data-type=\"png\" data-w=\"540\" style=\"\" src=\"./assets/17423802868400.1846301817135647.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006253\" data-ratio=\"2.291512915129151\" data-s=\"300,640\" data-type=\"png\" data-w=\"542\" style=\"\" src=\"./assets/17423802869810.3280582640279357.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 22px;font-weight: 700;letter-spacing: normal;text-align: center;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-weight: 700;letter-spacing: normal;text-wrap: wrap;font-size: 16px;text-align: left;background-color: rgb(255, 255, 255);'>Example 2\u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-weight: 700;letter-spacing: normal;text-wrap: wrap;font-size: 16px;text-align: left;background-color: rgb(255, 255, 255);'>: Bartender\u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-weight: 700;letter-spacing: normal;text-wrap: wrap;font-size: 16px;text-align: left;background-color: rgb(255, 255, 255);'>Sister Calculator\u003C/span>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006254\" data-ratio=\"0.4457593688362919\" data-s=\"300,640\" data-type=\"png\" data-w=\"1014\" style=\"\" src=\"./assets/17423802871300.9147896633680574.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006255\" data-ratio=\"0.6964856230031949\" data-s=\"300,640\" data-type=\"png\" data-w=\"626\" style=\"\" src=\"./assets/17423802871850.5522544528158073.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-weight: 700;letter-spacing: normal;text-wrap: wrap;font-size: 16px;text-align: left;background-color: rgb(255, 255, 255);'>Example 3\u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-weight: 700;letter-spacing: normal;text-wrap: wrap;font-size: 16px;text-align: left;background-color: rgb(255, 255, 255);'>: Help the programmer fix bugs\u003C/span>\u003Cspan style=\"letter-spacing: 0em;\">\u003C/span>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006256\" data-ratio=\"1.3333333333333333\" data-s=\"300,640\" data-type=\"png\" data-w=\"804\" style=\"\" src=\"./assets/17423802868920.5440253786357983.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006257\" data-ratio=\"1.2891566265060241\" data-s=\"300,640\" data-type=\"png\" data-w=\"830\" style=\"\" src=\"./assets/17423802870030.47550038744008427.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-weight: 700;letter-spacing: normal;text-wrap: wrap;font-size: 16px;text-align: left;background-color: rgb(255, 255, 255);'>Example 4\u003C/span>\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-weight: 700;letter-spacing: normal;text-wrap: wrap;font-size: 16px;text-align: left;background-color: rgb(255, 255, 255);'>: Provide examples (Few-Shot) for logical error detection\u003C/span>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006258\" data-ratio=\"0.9044117647058824\" data-s=\"300,640\" data-type=\"png\" data-w=\"544\" style=\"\" src=\"./assets/17423802886450.9194009082308092.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006259\" data-ratio=\"0.9148148148148149\" data-s=\"300,640\" data-type=\"png\" data-w=\"540\" style=\"\" src=\"./assets/17423802869810.4409940048189196.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006260\" data-ratio=\"0.9014598540145985\" data-s=\"300,640\" data-type=\"png\" data-w=\"548\" style=\"\" src=\"./assets/17423802875020.03332024057582306.png\">\u003Cspan style=\"letter-spacing: 0em;text-align: left;\">\u003C/span>\u003C/p>\u003C/span>\u003C/h2>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);cursor: pointer;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\"cursor: pointer;font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Features:\u003C/span>\u003C/h2>\u003Cul style='margin-top: 8px;margin-bottom: 8px;cursor: pointer;padding-left: 25px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);' class=\"list-paddingleft-1\">\u003Cli style=\"cursor: pointer;\">\u003Csection style=\"cursor: pointer;margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">\u003Cp style=\"cursor: pointer;color: rgb(0, 0, 0);line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">: MiniCPM-V 2.6 achieved an average score of 65.2 points in the latest version of OpenCompass evaluation, which integrates 8 popular benchmarks. With only 8 billion parameters, it surpasses widely-used proprietary models such as GPT-4o mini, GPT-4V, Gemini 1.5 Pro, and Claude 3.5 Sonnet in single-image understanding.\u003C/p>\u003C/section>\u003C/li>\u003Cli style=\"cursor: pointer;\">\u003Csection style=\"cursor: pointer;margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">\u003Cp style=\"cursor: pointer;color: rgb(0, 0, 0);line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">: MiniCPM-V 2.6 is also capable of dialogues and reasoning with multiple images, achieving industry-leading performance in popular multi-image benchmarks such as Mantis-Eval, BLINK, Mathverse mv, and Sciverse mv, while demonstrating promising contextual learning abilities.\u003C/p>\u003C/section>\u003C/li>\u003Cli style=\"cursor: pointer;\">\u003Csection style=\"cursor: pointer;margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">\u003Cp style=\"cursor: pointer;color: rgb(0, 0, 0);line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">: MiniCPM-V 2.6 accepts video input and performs exceptionally well in dialogues involving spatiotemporal information and dense caption generation. In the Video-MME test, it outperforms GPT-4V, Claude 3.5 Sonnet, and LLaVA-NeXT-Video-34B, regardless of whether subtitles are present or not.\u003C/p>\u003C/section>\u003C/li>\u003Cli style=\"cursor: pointer;\">\u003Csection style=\"cursor: pointer;margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">\u003Cp style=\"cursor: pointer;color: rgb(0, 0, 0);line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">: MiniCPM-V 2.6 can process images of any aspect ratio, supporting up to 1.8 million pixels (e.g., 1344x1344) for image processing. In the OCRBench test, it achieved industry-leading results, surpassing proprietary models such as GPT-4o, GPT-4V, and Gemini 1.5 Pro. Based on the latest RLAIF-V and VisCPM technologies, it exhibits reliable behavioral characteristics with a significantly lower object hallucination rate compared to GPT-4o and GPT-4V, and supports multiple languages including English, Chinese, German, French, Italian, Korean, and more.\u003C/p>\u003C/section>\u003C/li>\u003Cli style=\"cursor: pointer;\">\u003Csection style=\"cursor: pointer;margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">\u003Cp style=\"cursor: pointer;color: rgb(0, 0, 0);line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">: In addition to its compact size, MiniCPM-V 2.6 also demonstrates industry-leading token density (i.e., the number of pixels encoded per visual token). When processing an image with 1.8 million pixels, it generates only 640 tokens, which is 75% fewer than most models. This directly improves inference speed, first-token latency, memory usage, and power consumption. As a result, MiniCPM-V 2.6 can efficiently support real-time video understanding on edge devices such as iPads.\u003C/p>\u003C/section>\u003C/li>\u003Cli style=\"cursor: pointer;\">\u003Csection style=\"cursor: pointer;margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">\u003Cp style=\"cursor: pointer;color: rgb(0, 0, 0);line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">: MiniCPM-V 2.6 offers various user-friendly options: 1) llama.cpp and ollama support efficient CPU inference on local devices; 2) Provides quantized models in 16 different sizes in int4 and GGUF formats; 3) vLLM supports high-throughput and memory-efficient inference; 4) Fine-tuning for new domains and tasks is supported; 5) Quickly build local WebUI demos using Gradio; 6) An online web demo is provided.\u003C/p>\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);cursor: pointer;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\"cursor: pointer;font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Comparison\u003C/span>\u003C/h2>\u003Cp>\u003Cbr>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006250\" data-ratio=\"0.7212962962962963\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802875600.20208176521694177.png\">\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",[256,265,273,281,289,297,305,312],{"id":257,"title_md5":258,"publish_date":259,"author_md5":260,"is_original":23,"collection":261,"summary_md5":262,"cover_url":263,"cover_url_1_1":264},174,"bda05a4c84c53ba3437c1f5363ae96eb","2024-09-18","bc27fa490c4d0d525bac812fc0793534","#Elon Musk #All-In Summit 2024 #Nvidia","fab8efe359fa38ced92bfb896520874e","article_res/cover/f244d398c0ee0a7772cb9116263afbd1.jpeg","article_res/cover/802ee578f1e63ea0d375f95898f43d0d.jpeg",{"id":266,"title_md5":267,"publish_date":268,"author_md5":269,"is_original":4,"collection":5,"summary_md5":270,"cover_url":271,"cover_url_1_1":272},585,"e38a558d6338c26e2b0995f50d507f15","2022-04-01","8b3607d0f4181a3cb6ffdccf7185f09b","77ea62612ea76956676e7164032d7954","article_res/cover/8c2e262b00bc72ce5db1df6320ae8d0f.jpeg","article_res/cover/c228ee711a0876046271ba60cf3ff94e.jpeg",{"id":274,"title_md5":275,"publish_date":276,"author_md5":260,"is_original":23,"collection":277,"summary_md5":278,"cover_url":279,"cover_url_1_1":280},230,"2700effd8148411db487e01e22500d9c","2024-07-03","#AI Video Generator","7b90e56d79cc9896fe5cc115bf76ecf8","article_res/cover/cb99534c58c625dca7891a6293186620.jpeg","article_res/cover/c0329f1fab81e9034fa89c5cb51ff145.jpeg",{"id":282,"title_md5":283,"publish_date":284,"author_md5":260,"is_original":23,"collection":285,"summary_md5":286,"cover_url":287,"cover_url_1_1":288},179,"c1319bc77ef0f21939e94d1a167944a4","2024-09-08","#AI Avatar #ByteDance","2fbad24b55db29159d47fdea5fe6ce3c","article_res/cover/4e2cf7ed5950551074b080d9d69c5c1f.jpeg","article_res/cover/53e3d3af86f031aa1eaf8e09dbf786ce.jpeg",{"id":290,"title_md5":291,"publish_date":292,"author_md5":260,"is_original":23,"collection":293,"summary_md5":294,"cover_url":295,"cover_url_1_1":296},208,"bb09f6e9ee7b76cc84fe0a2f072abbb4","2024-07-31","#Meta #Object Detection","0217e96a00b183d55b207375fbd43bb2","article_res/cover/fd1b90586fee909b10777e47d561f409.jpeg","article_res/cover/d30b0789f086ae58ad87acd922eb7a19.jpeg",{"id":298,"title_md5":299,"publish_date":300,"author_md5":260,"is_original":23,"collection":301,"summary_md5":302,"cover_url":303,"cover_url_1_1":304},22,"ca9cb2b2606dc06480f2ea840bfd23a8","2025-03-01","#AI Video Generation #Alibaba #Wan #StepFun #SkyReels","6b5ee571c8e11a655d98d261bec1ee22","article_res/cover/cbb7d2892fdc47f5fe8d8c2972ced24e.jpeg","article_res/cover/db252440a3a3458792fd230884bc588a.jpeg",{"id":306,"title_md5":307,"publish_date":308,"author_md5":269,"is_original":4,"collection":5,"summary_md5":309,"cover_url":310,"cover_url_1_1":311},538,"9e175105c717232b13db57a7d5ea054d","2022-05-18","08d95b68b09b857308ae87eb858a5fb4","article_res/cover/b4bdaf3ad2b4a47ab3ebad75a3b00203.jpeg","article_res/cover/521483f5da0d6a99634c7d56f04df700.jpeg",{"id":313,"title_md5":314,"publish_date":315,"author_md5":260,"is_original":23,"collection":316,"summary_md5":317,"cover_url":318,"cover_url_1_1":319},98,"e33c7190eea3c5235f83a96da09ce9a8","2024-12-17","#AI Video Generator #Sora #Pika","1224923af65fd20370dc02e30ec1397f","article_res/cover/3b86e85d03fff4f356a3e4cf2bb329c9.jpeg","article_res/cover/5fa5c20ad0b40f8f544d257c0ef02938.jpeg",{"related":321,"small":360},[322,330,338,346,353],{"id":323,"publish_date":324,"is_original":23,"collection":325,"cover_url":326,"cover_url_1_1":327,"title":328,"summary":329,"author":28},21,"2025-03-02","#AI Agents #Magma #Microsoft #vision-language #Robot","article_res/cover/525b1439ef5286ee1a11342c6cd90a77.jpeg","article_res/cover/c5fe991a13b02d9086cf781631fa97eb.jpeg","Microsoft's Magma: The First Foundation Model for Multimodal AI Agents","Magma: A Foundation Model for Multimodal AI Agents",{"id":331,"publish_date":332,"is_original":23,"collection":333,"cover_url":334,"cover_url_1_1":335,"title":336,"summary":337,"author":28},82,"2025-01-02","#SITUATIONAL AWARENESS #ASI #AGI","article_res/cover/459be2942ab507050cf08f417e9e0417.jpeg","article_res/cover/96a964fa28ca8b6ef2bc2b19338bb146.jpeg","From AGI to Superintelligence: The Big Bang of Intelligence","AI progress won't stop at human-level.",{"id":339,"publish_date":340,"is_original":23,"collection":341,"cover_url":342,"cover_url_1_1":343,"title":344,"summary":345,"author":28},94,"2024-12-21","#Google #o1 #LLM #Gemini","article_res/cover/0978cc05f28f10330ab5289902cf6003.jpeg","article_res/cover/e13e8d924455d80dda7fa1120a61b2d8.jpeg","Google releases Gemini 2.0 Flash Thinking Mode - comparable to o1 Pro","generate the \"thinking process\"",{"id":347,"publish_date":348,"is_original":4,"collection":5,"cover_url":349,"cover_url_1_1":350,"title":351,"summary":352,"author":28},427,"2023-07-27","article_res/cover/1dc42c888292562986f633ef2dc7fa04.jpeg","article_res/cover/05f91a6a05f6f206b2be5065343dca58.jpeg","AI image processing tool - Flair.ai trial","THE AI DESIGN TOOL FOR BRANDED CONTENT",{"id":354,"publish_date":355,"is_original":23,"collection":5,"cover_url":356,"cover_url_1_1":357,"title":358,"summary":359,"author":28},193,"2024-08-18","article_res/cover/b2b70461b9c8d8321e0e68e98317b113.jpeg","article_res/cover/cf7d9a8690597660c65ab92b89db86b6.jpeg","System Dynamics 101","Recently started learning the systems dynamics course by MIT Professor John Sterman.",[361,367,373],{"title":10,"list":362},[363,364,365,366],{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"title":222,"list":368},[369,370,371,372],{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"id":227,"publish_date":228,"is_original":23,"collection":229,"cover_url":230,"cover_url_1_1":231,"title":232,"summary":233,"author":28},{"id":235,"publish_date":236,"is_original":23,"collection":73,"cover_url":237,"cover_url_1_1":238,"title":239,"summary":240,"author":28},{"title":242,"list":374},[],[8,9,10],[8,12,13,14,9,10,15,16,17,18],["Reactive",245],1754646419847]