[{"data":1,"prerenderedAt":373},["ShallowReactive",2],{"$fgukOamtKU1RtUiMFsqdObttmqPPQz0uc7bl_gj_LyX0":3,"$f9zx8DTQbzBcbC0LVAcvdzaoy0S3weniaX4NHvFc0wTw":245,"article-307":372},{"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":249,"articles_id":250,"cover_url":251,"cover_url_1_1":252,"title":253,"summary":254,"author":28,"content":255,"popular":256,"list":315,"category":370,"tag":371},307,"2024-03-28","#LLM","BA213P8M-lCNvSpJnhemuQ","article_res/cover/27c22d877aa4d827c74730a40932ef64.jpeg","article_res/cover/b925b57062ba315da3067ee08426cf12.jpeg","Large Language Models: A Survey","Scaling - a power law between compute, training data size and number of model parameters.","\u003Cdiv class=\"rich_media_content js_underline_content\n                       autoTypeSetting24psection\n            \" id=\"js_content\">\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Recently, I read a paper published last month titled \"Large Language Models: A Survey.\" https://arxiv.org/abs/2402.06196\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>This article explores the astonishing performance of large language models (LLMs) in various natural language processing tasks since the release of ChatGPT in November 2022, examining how LLMs are changing the way we interact with technology.\u003C/p>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>Article abstract\u003C/h2>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">It reviews several of the most prominent large language models, including the three major popular series GPT, LLaMA, and PaLM, discussing their characteristics, contributions, and limitations.\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">It outlines the technical approaches for building and enhancing large language models, surveys popular datasets prepared for training, fine-tuning, and evaluating LLMs, reviews widely used evaluation metrics, and compares the performance of several popular models across a range of representative benchmarks.\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">By discussing future research directions and challenges, it provides readers with a development blueprint for the field of large language model research.\u003C/section>\u003C/li>\u003C/ul>\u003Csection data-tool=\"mdnice编辑器\" data-website=\"https://www.mdnice.com\" style=\"font-size: 16px;color: black;padding: 0 10px;line-height: 1.6;word-spacing: 0px;letter-spacing: 0px;word-break: break-word;word-wrap: break-word;text-align: left;font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, 'PingFang SC', Cambria, Cochin, Georgia, Times, 'Times New Roman', serif;\">\u003Cp data-tool=\"mdnice编辑器\" style=\"font-size: 16px;padding-top: 8px;padding-bottom: 8px;margin: 0;line-height: 26px;color: black;\">\u003Cspan style='color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>You can read the original text, but I have extracted various tables from it and visualized them to help you understand.\u003C/span>\u003C/p>\u003C/section>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>1. Classification of LLMs\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003986\" data-ratio=\"0.6342592592592593\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810644440.8620150517028218.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">By parameter size\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">By category\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">By openness\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Nativity\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>2. Overview of LLMs\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003974\" data-ratio=\"0.9685185185185186\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810644460.21654427693366962.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Provides a brief introduction to different series of LLMs, including their classification, parameter size, and training datasets.\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">The situation of the three giants: OpenAI, Meta, and Google\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>3. Capability map of LLMs\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003973\" data-ratio=\"0.44722222222222224\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810644480.15610926355257537.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Explores the impressive performance of LLMs in various natural language processing tasks, such as understanding, multilingualism, knowledge, code, reasoning, and dialogue.\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>4. Scaling Law\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003978\" data-ratio=\"0.5305555555555556\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810644950.2612307249537824.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">As the number of model parameters increases, their ability to understand and utilize contextual information also improves.\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>5. Milestones of LLMs\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003979\" data-ratio=\"0.49166666666666664\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810658410.4232174396165984.png\">\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Starting from the original Transformer, this concept was like a breath of fresh air that completely transformed the landscape of natural language processing. It was not just a model but a completely new approach that laid the foundation for subsequent developments. The emergence of BERT significantly enhanced the machine's ability to understand language by deeply comprehending contextual meaning, greatly improving the model's understanding capability. GPT-1 was another milestone, initiating the era of generative pre-trained models and laying the foundation for the subsequent GPT series.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;line-height: 26px;'>Over time, we have witnessed more innovations, each step continuously expanding the boundaries of large language models. In this process, some models were not only technological breakthroughs but also represented entirely new explorations of problem-solving methods. Others focused on methodological innovation; although they may not have had enormous parameter scales, they played an indispensable role in advancing the development of language models.\u003C/p>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>6. How Transformers work\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003983\" data-ratio=\"1.180515759312321\" data-s=\"300,640\" data-type=\"png\" data-w=\"698\" style=\"width: 255px;height: 301px;\" src=\"./assets/17423810647700.6830572705287625.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Introduces the basic principles of the Transformer model as a foundation for understanding LLMs.\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>7. How DPO works\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003984\" data-ratio=\"0.24351851851851852\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810658030.700462697853186.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Introduces the working principle of DPO (Direct Preference Optimization) and its application in LLMs. This has been shared before:\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>8. Technical details of LoRA (Low-Rank Adaptation) reparameterization\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003975\" data-ratio=\"0.728125\" data-s=\"300,640\" data-type=\"png\" data-w=\"640\" style=\"width: 318px;height: 232px;\" src=\"./assets/17423810655710.1977273077380557.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">In-depth discussion of LoRA technology and how it optimizes the parameterization process of LLMs.\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>9. Construction process of LLMs\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003980\" data-ratio=\"1.0898148148148148\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810664920.4018302196587673.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Explains the basic steps for constructing large language models, including data collection, model design, and training.\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;letter-spacing: normal;text-align: left;text-wrap: wrap;'>10. Usage and enhancement of LLMs\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003976\" data-ratio=\"0.6527777777777778\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810670180.7174216004780278.png\">\u003C/p>\u003Cul data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: rgb(0, 0, 0);font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, \"PingFang SC\", Cambria, Cochin, Georgia, Times, \"Times New Roman\", serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Usage methods and advantages of RAG models\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Application scenarios and methods for combining knowledge graphs (KG) with LLMs\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Enhancing the capabilities of LLMs using tools and platforms like HuggingGPT\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Technical details of agent-based conversational information retrieval\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">Application and importance of datasets in LLMs\u003C/section>\u003C/li>\u003C/ul>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",[257,265,273,276,283,291,299,307],{"id":23,"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},"2f37ba6fed8f66b0572a48249032efb5","2025-03-19","bc27fa490c4d0d525bac812fc0793534","#AI Story","04cf0fbb09a637eca029d7b523bbcbda","article_res/cover/09545320f42b7146e584067f0fd48946.jpeg","article_res/cover/df1a41705d2e7ae5c76705c30b0684af.jpeg",{"id":266,"title_md5":267,"publish_date":268,"author_md5":269,"is_original":23,"collection":5,"summary_md5":270,"cover_url":271,"cover_url_1_1":272},552,"4c6b59b807cd87944e25283c293a9bd9","2022-05-04","8936f53b23e9dfe2965d9e2ec23a4779","fd6e7c1af8ce6c247d8b12641f317b1d","article_res/cover/2b1d4e7150fc04a8a75f7214381d1a9c.jpeg","article_res/cover/1bcc7b2244f44a02ebad1fe9c0705d51.jpeg",{"id":21,"title_md5":274,"publish_date":22,"author_md5":260,"is_original":23,"collection":5,"summary_md5":275,"cover_url":24,"cover_url_1_1":25},"11aaec56e2b3e420ea476e019c0487b3","3624c8cab3a8417fd95bcdb265d6edb0",{"id":277,"title_md5":278,"publish_date":279,"author_md5":260,"is_original":23,"collection":5,"summary_md5":280,"cover_url":281,"cover_url_1_1":282},181,"12ce40ba4d74d5602dbb3d361694070f","2024-09-05","faec110f3693f67fa2e74b54b3c0691e","article_res/cover/b48bae2fa24f2eb5f42509d7b947847b.jpeg","article_res/cover/cb4207311294df2f35de2a5bfed622fa.jpeg",{"id":284,"title_md5":285,"publish_date":286,"author_md5":260,"is_original":4,"collection":287,"summary_md5":288,"cover_url":289,"cover_url_1_1":290},401,"9f5f20c45bfe685198d2d4728416d5e8","2023-10-01","#Object Detection #AI Agent #Langchain","0f56ed93fe5ce6ef3e13890e9f0a684c","article_res/cover/2dce58eb9163407c184896e9f1ce75b4.jpeg","article_res/cover/8c8d5cac60fb88a5d02561dc86bb97a0.jpeg",{"id":292,"title_md5":293,"publish_date":294,"author_md5":260,"is_original":23,"collection":295,"summary_md5":296,"cover_url":297,"cover_url_1_1":298},46,"d89b72d178b80d754069b4e0b16683ed","2025-02-07","#Bytedance #AI Avatar #AI Video Generator","506910d5a17ab6dee1ae6e322841d330","article_res/cover/5000b160051edfc2e45d5a5b93640159.jpeg","article_res/cover/80696be2904b86eb303ad4dbd6dbdbec.jpeg",{"id":300,"title_md5":301,"publish_date":302,"author_md5":260,"is_original":4,"collection":303,"summary_md5":304,"cover_url":305,"cover_url_1_1":306},446,"85d009a6d3fcdb101737e1c4d9998e4d","2023-06-05","#AI Game #AI Image Generator","c4b849fa677554d214d86dc00d05d7a1","article_res/cover/41a72252ba6dbaaa316216970274a830.jpeg","article_res/cover/5db4ed377e73960b0a1945422681e7a4.jpeg",{"id":308,"title_md5":309,"publish_date":310,"author_md5":260,"is_original":23,"collection":311,"summary_md5":312,"cover_url":313,"cover_url_1_1":314},80,"63550e3e817d4b445c2e19430473c52c","2025-01-04","#Google #AI Video Editor","3a4869b9a8e67f642938738ca18b3a22","article_res/cover/244ba813af9084ab8b2fb42748da185d.jpeg","article_res/cover/4af914a0a7176eac1a45541f144a623a.jpeg",{"related":316,"small":355},[317,324,331,339,347],{"id":318,"publish_date":319,"is_original":23,"collection":320,"cover_url":321,"cover_url_1_1":322,"title":323,"summary":5,"author":28},133,"2024-11-08","#AI Code Generator","article_res/cover/c919553e30cadce7fad37fe835f06439.jpeg","article_res/cover/454605e3395c7a89ab94f834888b9dfa.jpeg","Cursor - The AI Code Editor",{"id":325,"publish_date":326,"is_original":23,"collection":320,"cover_url":327,"cover_url_1_1":328,"title":329,"summary":330,"author":28},112,"2024-12-03","article_res/cover/42bf26f9f2ca5af22ef473673cb9f518.jpeg","article_res/cover/9aaa9c965e49781053a5e7aeb3491173.jpeg","Cursor co-founder Arvid Lunnemark's blog","Why is teleportation hard?  \nWhy is it so expensive to build tunnels?",{"id":332,"publish_date":333,"is_original":23,"collection":334,"cover_url":335,"cover_url_1_1":336,"title":337,"summary":338,"author":28},26,"2025-02-26","#AI Research #Nvidia","article_res/cover/a49545e2ad00521f5e7e1c5670e6003b.jpeg","article_res/cover/c9e76abe1708cc4a775f6bea0a3afc96.jpeg","Stanford and NVIDIA's Evo 2 - Large AI Model for Biomolecular Sciences","Genome modeling and design across all domains of life with Evo 2",{"id":340,"publish_date":341,"is_original":4,"collection":342,"cover_url":343,"cover_url_1_1":344,"title":345,"summary":346,"author":28},129,"2024-11-12","#OpenAI #AI Code Generator #LLM #o1","article_res/cover/6654db2a98aadeea109fc3364da389c7.jpeg","article_res/cover/b1e5e6d6a62fb9b205ac09b16c6a25da.jpeg","OnBoard! Podcast Notes - EP 62: OpenAI o1 and the New Paradigm of LLM + Reinforcement Learning (1)","EP 62. A deep interpretation of Google Deepmind and LLM researchers on OpenAI o1 and the new paradigm of LLM + reinforcement learning",{"id":348,"publish_date":349,"is_original":4,"collection":5,"cover_url":350,"cover_url_1_1":351,"title":352,"summary":353,"author":354},604,"2022-03-13","article_res/cover/b1e7e12d55932a445e91d45f896c486a.jpeg","article_res/cover/0c07557158250cca3a12a1ea1b9d9a48.jpeg","How to read financial statements - CF Statement of Cash Flows","Why focus on cash flows? Because a share of stock is a","Course notes",[356,362,368],{"title":10,"list":357},[358,359,360,361],{"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":363},[364,365,366,367],{"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":369},[],[8,9,10],[8,12,13,14,9,10,15,16,17,18],["Reactive",245],1754646414623]