[{"data":1,"prerenderedAt":380},["ShallowReactive",2],{"$fgukOamtKU1RtUiMFsqdObttmqPPQz0uc7bl_gj_LyX0":3,"$fAXRbAqUBE1yTPw44IJXZG-5P04_WB85mNVvV8AoXYC8":245,"article-242":379},{"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":319,"category":377,"tag":378},242,"2024-06-18","#AI Avatar #Lip Sync","06XivIzacDbrdauLpyPwEQ","article_res/cover/962521d82eac2b5cf90b12ec083495d6.jpeg","article_res/cover/55537cb0bfe54667c4d8ccffaa064c1c.jpeg","Making Avatar Move - InstructAvatar, EMO, Follow-Your-Emoji","Text-Guided Emotion and Motion Control for Avatar Generation","\u003Cdiv class=\"rich_media_content js_underline_content\n                       autoTypeSetting24psection\n            \" id=\"js_content\">\u003Cp>\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;'>Following yesterday's two lip-sync projects from Tencent,\u003C/span>\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;'>today I will share three more.\u003C/span>\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;'>\u003C/span>\u003C/p>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;text-wrap: wrap;color: black;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;'>InstructAvatar\u003C/h2>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;text-wrap: wrap;color: black;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;line-height: 26px;'>: InstructAvatar is a tool for generating Avatars with text-guided emotion and motion control.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;text-wrap: wrap;color: black;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;line-height: 26px;'>\u003Cstrong>Link\u003C/strong>：https://github.com/wangyuchi369/InstructAvatar\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;text-wrap: wrap;color: black;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;line-height: 26px;'>: Peking University\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;text-wrap: wrap;color: black;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;line-height: 26px;'>\u003Cstrong>Scene\u003C/strong>：\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;text-wrap: wrap;color: black;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;'>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">Emotional speech control\u003C/p>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423804386810.03892792742182327.mp4\" poster=\"./assets/17423804382010.49284734139342756.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">Facial motion control\u003C/p>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423804386650.40739218553273404.mp4\" poster=\"./assets/17423804381730.4361762710053845.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003C/ul>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;text-wrap: wrap;color: black;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;line-height: 26px;'>\u003Cstrong>Model architecture\u003C/strong>：\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100005065\" data-ratio=\"0.4111111111111111\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423804609050.7419873602139822.png\">\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;text-wrap: wrap;color: black;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;line-height: 26px;'>InstructAvatar consists of two components: VAE H for disentangling motion information from videos, and Motion Generator G for generating motion latent variables conditioned on audio and instructions. Since the model has two types of data, two switches are designed in the instructions and audio. During inference, the motion encoder in the VAE will be discarded, and the predicted motion latent variable will be obtained by iterative denoising Gaussian noise. Combined with the user-provided portrait, the final video is generated through the decoder of the VAE.\u003C/p>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: black;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;'>EMO\u003C/h2>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>: EMO is a tool that generates expressive human portrait videos via an Audio2Video diffusion model under weak conditions.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>\u003Cstrong>Link\u003C/strong>：https://github.com/HumanAIGC/EMO\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>: Alibaba\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>\u003Cstrong>Scene\u003C/strong>：\u003C/p>\u003Col data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: black;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);\">\u003Cstrong style=\"color: black;\">Singing\u003C/strong>\u003C/section>\u003C/li>\u003C/ol>\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: black;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);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">\u003Cstrong>Make portraits sing\u003C/strong>\u003C/p>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423804391770.980717687179284.mp4\" poster=\"./assets/17423804381740.08620462084559422.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">\u003Cstrong>Different languages and portrait styles\u003C/strong>\u003C/p>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423804423670.8753416225791886.mp4\" poster=\"./assets/17423804392280.10930686920574662.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">\u003Cstrong>Rap\u003C/strong>\u003C/p>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423804407730.06262194408251598.mp4\" poster=\"./assets/17423804381990.3071415680903351.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003C/ul>\u003Col start=\"2\" data-tool=\"mdnice编辑器\" class=\"list-paddingleft-1\" style='margin-top: 8px;margin-bottom: 8px;padding-left: 25px;width: 557.438px;color: black;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);\">\u003Cstrong style=\"color: black;\">Speaking\u003C/strong>\u003C/section>\u003C/li>\u003C/ol>\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: black;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);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">\u003Cstrong>Converse with different characters\u003C/strong>\u003C/p>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423804607380.12028959716910426.mp4\" poster=\"./assets/17423804391760.6047387989263298.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">\u003Cstrong>Cross-actor performance\u003C/strong>\u003C/p>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423804418340.30063823193416095.mp4\" poster=\"./assets/17423804388740.4905526769163686.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003C/ul>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>\u003Cstrong>Model architecture\u003C/strong>：\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100005066\" data-ratio=\"0.7092592592592593\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423804609210.036573370171256725.png\">\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>The method framework proposed by EMO mainly includes two stages. In the initial stage, i.e., the frame encoding stage, ReferenceNet extracts features from reference images and motion frames. Subsequently, in the diffusion process stage, the pre-trained audio encoder processes audio embeddings. Facial region masks are combined with multi-frame noise to control the generation of facial images. Next, the backbone network is used for denoising operations. In the backbone network, two attention mechanisms are applied: reference attention and audio attention. These mechanisms are crucial for maintaining character identity and modulating character actions. Additionally, a temporal module is utilized to manipulate the temporal dimension and adjust the speed of motion.\u003C/p>\u003Ch2 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 22px;color: black;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;'>Follow-Your-Emoji\u003C/h2>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>: Follow-Your-Emoji is a diffusion-based portrait animation framework that animates a reference portrait using target landmark sequences. The main challenges in portrait animation are maintaining the identity of the reference portrait, conveying the target expression, while preserving temporal consistency and realism.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100005207\" data-ratio=\"0.5555555555555556\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423804609220.9685684756159225.png\">\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>\u003Cstrong>Link\u003C/strong>：https://follow-your-emoji.github.io/\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>: The University of Hong Kong, Tencent, Tsinghua University\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>\u003Cstrong>Scene\u003C/strong>：\u003C/p>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423804445420.7194360591463718.mp4\" poster=\"./assets/17423804390760.36434175500159305.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\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: black;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);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">Single action + multiple portraits\u003C/p>\u003C/section>\u003Cp style=\"text-align: center;\">\u003Cspan style=\"display: none;line-height: 0px;\">‍\u003C/span>\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100005204\" data-ratio=\"0.16666666666666666\" data-s=\"300,640\" data-type=\"gif\" data-w=\"1080\" style=\"\" src=\"./assets/17423804609470.4621630942214856.gif\">\u003C/p>\u003C/li>\u003Cli>\u003Csection style=\"margin-top: 5px;margin-bottom: 5px;line-height: 26px;color: rgb(1, 1, 1);\">\u003Cp style=\"padding-top: 8px;padding-bottom: 8px;line-height: 26px;color: black;\">Single portrait + multiple actions\u003C/p>\u003C/section>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100005205\" data-ratio=\"0.16666666666666666\" data-s=\"300,640\" data-type=\"gif\" data-w=\"1080\" style=\"\" src=\"./assets/17423804613790.3398262404998287.gif\">\u003C/p>\u003C/li>\u003C/ul>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;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;'>Model architecture\u003C/h3>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100005206\" data-ratio=\"0.774074074074074\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423804612470.24238345700035246.png\">\u003C/p>\u003Ch3 data-tool=\"mdnice编辑器\" style='margin-top: 30px;margin-bottom: 15px;font-weight: bold;font-size: 20px;color: black;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;'>\u003C/h3>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>Firstly, use the landmark encoder to extract features from the expression-aware landmark sequence and fuse these features with multi-frame noise.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>Then, randomly mask the frames of the input latent sequence using a progressive strategy.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>Finally, concatenate this latent sequence with the fused multi-frame noise and input it into the denoising U-Net for denoising processing to generate the video.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>The appearance network and image prompt injection module help the model maintain the identity of the reference portrait, while temporal attention maintains temporal consistency.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>During training, the facial fine loss guides the U-Net to focus more on the generation of faces and expressions.\u003C/p>\u003Cp data-tool=\"mdnice编辑器\" style='margin-bottom: 0px;padding-top: 8px;padding-bottom: 8px;color: black;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;'>During inference, referring to AniPortrait, use the motion alignment module to align the target landmarks with the reference portrait. Then, generate keyframes first and predict long videos using a progressive strategy.\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",[257,265,269,277,286,295,303,311],{"id":258,"title_md5":259,"publish_date":260,"author_md5":261,"is_original":4,"collection":5,"summary_md5":262,"cover_url":263,"cover_url_1_1":264},612,"4f08a2cf204db1a15524edc350138908","2022-03-05","4afa1f337c03df0a2e3454c8e9799662","271ede7e7f7532d11d6ab7058a213ebb","article_res/cover/f4d2fa0d94b461e9b789e1bd3fa08303.jpeg","article_res/cover/3eb745f44671dda43aacba4b0a16868c.jpeg",{"id":235,"title_md5":266,"publish_date":236,"author_md5":267,"is_original":23,"collection":73,"summary_md5":268,"cover_url":237,"cover_url_1_1":238},"6716106c7b424c2cd489a184d57a8668","bc27fa490c4d0d525bac812fc0793534","8a558d676a3e4987d7c6e45bf53663ec",{"id":270,"title_md5":271,"publish_date":272,"author_md5":267,"is_original":23,"collection":273,"summary_md5":274,"cover_url":275,"cover_url_1_1":276},276,"568613c631c126f4f2c279a10bdf3ede","2024-05-13","#AI Index Report 2024 #AI Agent #Embodied AI","d347fa575c19254fec93403c01609d91","article_res/cover/7da4e33e8b3ac59927da78791d766730.jpeg","article_res/cover/2dd7e18d50460747399b16f6fcc28766.jpeg",{"id":278,"title_md5":279,"publish_date":280,"author_md5":281,"is_original":4,"collection":282,"summary_md5":283,"cover_url":284,"cover_url_1_1":285},456,"e0bbc6133bd79cb5f37523c9d93549e8","2023-05-17","aaa8ca17ae2e86c309dea80b10f6e68d","#Prompt Engineering","ae29edcd094bc79e8fbda074bb9b7172","article_res/cover/4e52f03409b84713991814f06fd6424d.jpeg","article_res/cover/3a58bf9a788ec37b5d5275f0755c1791.jpeg",{"id":287,"title_md5":288,"publish_date":289,"author_md5":290,"is_original":4,"collection":291,"summary_md5":292,"cover_url":293,"cover_url_1_1":294},422,"4a52722050dc163a76ec0550c12af45a","2023-08-09","cfab1ba8c67c7c838db98d666f02a132","#LLM","1f7fd24c7d510ffe2c7b0e16b2815592","article_res/cover/333388145626f84ced5762dba425a64d.jpeg","article_res/cover/27249377525a79a36fc10bd7c09ee374.jpeg",{"id":296,"title_md5":297,"publish_date":298,"author_md5":267,"is_original":4,"collection":299,"summary_md5":300,"cover_url":301,"cover_url_1_1":302},391,"20b37e9bc4593beb027d025b68b80eb0","2023-10-17","#AI Animation","9fa815c6e87b6caa12e87af134b04a3c","article_res/cover/83dc42e9806d1d6622e2f5141d9c34ad.jpeg","article_res/cover/351b6c2c111e7adf91e79ccfe5edf004.jpeg",{"id":304,"title_md5":305,"publish_date":306,"author_md5":307,"is_original":4,"collection":5,"summary_md5":308,"cover_url":309,"cover_url_1_1":310},546,"f920184fbbe46872e1c0eaba0c6198cb","2022-05-10","70537b1aee8f8d5429894e91ceae53b9","018edc9254af2f1fa4e13a6ecb5ceb96","article_res/cover/306c699f36a8cc19ff5d3b925cbb140e.jpeg","article_res/cover/d3a80000741cbeea17c008ad002b5613.jpeg",{"id":312,"title_md5":313,"publish_date":314,"author_md5":267,"is_original":23,"collection":315,"summary_md5":316,"cover_url":317,"cover_url_1_1":318},256,"2cfd4df7d23c4f8db0273155aa9e6711","2024-06-04","#AI Video Generator #Sora","e361baa2f7aaa682be3c0554e5363aa2","article_res/cover/f8f4418b88fd1a7399af611af75b5c19.jpeg","article_res/cover/11e860f728d6be033979d66a452d3344.jpeg",{"related":320,"small":362},[321,329,337,345,354],{"id":322,"publish_date":323,"is_original":23,"collection":324,"cover_url":325,"cover_url_1_1":326,"title":327,"summary":328,"author":28},76,"2025-01-07","#AI Video Generation #Google","article_res/cover/3613b008d99e99c267bce18c2c7f4003.jpeg","article_res/cover/055bce99535eb3d30085f963064e930a.jpeg","Vision Transformer (ViT)","An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale",{"id":330,"publish_date":331,"is_original":23,"collection":332,"cover_url":333,"cover_url_1_1":334,"title":335,"summary":336,"author":28},66,"2025-01-19","#Google #Imagen3 #AI Image Generator","article_res/cover/56ae40decdd38deb3bc1b59a2efa02ed.jpeg","article_res/cover/8df243692026cd39a5b6ecbe2c6ec2ec.jpeg","Google Whisk: Visualize and remix ideas using images and AI","Whisk: Visualize and remix ideas using images and AI",{"id":338,"publish_date":339,"is_original":23,"collection":340,"cover_url":341,"cover_url_1_1":342,"title":343,"summary":344,"author":28},45,"2025-02-08","#AI Agent #Object Detection","article_res/cover/b6dc16af6eeb0bf4f16993e2d31500c7.jpeg","article_res/cover/52519e83aef4083ebdf78cc303244a7a.jpeg","Andrew Ng's latest release on Agent target detection: Agentic Object Detection","Reasoning-driven object detection: human-like precision via text prompts without the overhead of custom training",{"id":346,"publish_date":347,"is_original":23,"collection":348,"cover_url":349,"cover_url_1_1":350,"title":351,"summary":352,"author":353},500,"2022-11-14","#Psychology","article_res/cover/10ae0ea067b26277f2c3940ee3b6a909.jpeg","article_res/cover/e3a5b76ff75be407fc9c5c1390f8ac60.jpeg","A pessimistic optimist","\"There is one thing you cannot take away from a person, and that is the precious freedom. People always have the freedom to choose their own attitude and behavior in any environment.\" - Frankl","Psychological counseling notes",{"id":355,"publish_date":356,"is_original":23,"collection":357,"cover_url":358,"cover_url_1_1":359,"title":360,"summary":361,"author":28},28,"2025-02-24","#Andrej Karpathy #Deep Dive into LLMs #LLM #RL #DeepSeek","article_res/cover/db62a8c43fa565112c0aefa8776e1de2.jpeg","article_res/cover/cbb4289951cb6a0cda64f8fd913a2e23.jpeg","DeepSeek-R1 - Andrej Karpathy in-depth explanation of LLM (Part 9)","DeepSeek R1",[363,369,375],{"title":10,"list":364},[365,366,367,368],{"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":370},[371,372,373,374],{"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":376},[],[8,9,10],[8,12,13,14,9,10,15,16,17,18],["Reactive",245],1754646417373]