[{"data":1,"prerenderedAt":376},["ShallowReactive",2],{"$fgukOamtKU1RtUiMFsqdObttmqPPQz0uc7bl_gj_LyX0":3,"$fIszBPilF8xDiQPnYmnZKoUXkTt-gXH25QgG7sXq6dHw":245,"article-304":375},{"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":323,"category":373,"tag":374},304,"2024-03-31","#AI 3D Generator #Alibaba","QgQCm01bIbjL0FNMZUhvRw","article_res/cover/ada359e9be0723ea379baafd3514a568.jpeg","article_res/cover/0c880907c00d3a0ed456afbdbaee751b.jpeg","Champ - Generating animations from static human image pictures","Controllable and Consistent Human Image Animation with 3D Parametric Guidance","\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: 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;'>Today, I will share a paper from Nanjing University, Fudan University, and Alibaba: \"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance\".\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;'>Effect\u003C/h2>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423810712190.21398325018930975.mp4\" poster=\"./assets/17423810705220.10327482377211084.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\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;'>Project Introduction\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;'>Champ is a method for human image animation that uses a 3D parametric human body model within a latent diffusion framework to enhance shape alignment and motion guidance in current human generation technologies. This method leverages the SMPL (Skinned Multi-Person Linear) model as a 3D parametric human body model, establishing a unified representation of body shape and posture. This helps accurately capture complex human geometry and motion features from the source video. Specifically, Champ integrates rendered depth images, normal maps, and semantic maps obtained from SMPL sequences, along with skeleton-based motion guidance, enriching detailed 3D shapes and pose attributes into the conditions of the latent diffusion model. Champ employs a multi-layer motion fusion module incorporating self-attention mechanisms to fuse shape and motion latent representations in the spatial domain. By representing the 3D human parametric model as motion guidance, Champ can perform parameterized shape alignment between reference images and source video motions. Experimental evaluations conducted on benchmark datasets show that this method generates high-quality human animations that accurately capture pose and shape changes. Additionally, Champ demonstrates superior generalization capabilities on the proposed wild dataset.\u003C/p>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423810733980.32015547959533475.mp4\" poster=\"./assets/17423810705250.7111480296202453.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\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;'>Showcases\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004047\" data-ratio=\"0.4981481481481482\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"display: inline;\" src=\"./assets/17423810737100.8414701425473503.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;'>\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;'>The proposed method showcases a novel capability to generate temporally coherent and visually realistic human image animations by utilizing reference images and pre-defined action sequences combined with a 3D parametric human body model. Furthermore, it demonstrates enhanced abilities to improve shape alignment and motion guidance in the generated videos. This approach facilitates animating various types of characters, including portraits that exhibit significant domain changes, such as:\u003C/span>\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;'>(a) A neoclassical oil painting depicting a woman wearing a white dress and fur coat.\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;'>(b) A watercolor portrait of a woman.\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;'>(c) An oil painting titled \"Queen of Armenia.\"\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;'>In addition, it is capable of animating characters derived from text-to-image diffusion models, including the following prompts:\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;'>(d) A portrait of a woman in a yellow dress, heavy metal comic book cover art, space theme.\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;'>(e) A woman posing in a silver dress, popular on CG Society, futuristic, bright blue eyes.\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;'>(f) A realistic depiction of Aang from The Last Airbender, showcasing his mastery of all bending elements in the powerful Avatar State.\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;'>Framework\u003C/h2>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004048\" data-ratio=\"0.6407407407407407\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810736960.38677348301682213.png\">\u003C/p>\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;'>Multi-level motion conditions and their corresponding cross-attention maps.\u003C/span>\u003C/p>\u003C/section>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004049\" data-ratio=\"0.4740740740740741\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810736980.6213369279729952.png\">\u003C/p>\u003Cp style=\"text-align: left;\">\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;'>Each set of images (top) includes representations of depth maps, normal maps, semantic maps, and DWpose skeletons rendered from the corresponding SMPL sequences. Subsequent images (bottom) display the outputs guided by self-attention.\u003C/span>\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;'>Comparison\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;'>Qualitative comparison with state-of-the-art methods on benchmark datasets.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004050\" data-ratio=\"0.6037037037037037\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810737180.5034533787230311.png\">\u003Cspan style='font-family: mp-quote, -apple-system-font, BlinkMacSystemFont, \"Helvetica Neue\", \"PingFang SC\", \"Hiragino Sans GB\", \"Microsoft YaHei UI\", \"Microsoft YaHei\", Arial, sans-serif;font-size: var(--articleFontsize);letter-spacing: 0.034em;text-align: justify;'>\u003C/span>\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;'>Qualitative comparison of animating unseen domain images.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004051\" data-ratio=\"0.3814814814814815\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810737100.3666693073379834.png\">\u003Cspan style='font-family: mp-quote, -apple-system-font, BlinkMacSystemFont, \"Helvetica Neue\", \"PingFang SC\", \"Hiragino Sans GB\", \"Microsoft YaHei UI\", \"Microsoft YaHei\", Arial, sans-serif;font-size: var(--articleFontsize);letter-spacing: 0.034em;text-align: justify;'>\u003C/span>\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;'>Comparison on shape change data.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100004052\" data-ratio=\"0.5277777777777778\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423810754820.7514343398547021.png\">\u003Cspan style='font-family: mp-quote, -apple-system-font, BlinkMacSystemFont, \"Helvetica Neue\", \"PingFang SC\", \"Hiragino Sans GB\", \"Microsoft YaHei UI\", \"Microsoft YaHei\", Arial, sans-serif;font-size: var(--articleFontsize);letter-spacing: 0.034em;text-align: justify;'>\u003C/span>\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",[257,266,274,282,290,298,306,314],{"id":258,"title_md5":259,"publish_date":260,"author_md5":261,"is_original":23,"collection":262,"summary_md5":263,"cover_url":264,"cover_url_1_1":265},179,"c1319bc77ef0f21939e94d1a167944a4","2024-09-08","bc27fa490c4d0d525bac812fc0793534","#AI Avatar #ByteDance","2fbad24b55db29159d47fdea5fe6ce3c","article_res/cover/4e2cf7ed5950551074b080d9d69c5c1f.jpeg","article_res/cover/53e3d3af86f031aa1eaf8e09dbf786ce.jpeg",{"id":267,"title_md5":268,"publish_date":269,"author_md5":270,"is_original":4,"collection":48,"summary_md5":271,"cover_url":272,"cover_url_1_1":273},477,"bae199b9df2ac0e835a5535cfa2f7533","2023-04-17","cfab1ba8c67c7c838db98d666f02a132","4d6782c23581852e87c549b3990689c6","article_res/cover/c5a44c456478ff6d86d849188972a479.jpeg","article_res/cover/e2d31d9dd62d181106af1a4e0ce62ccd.jpeg",{"id":275,"title_md5":276,"publish_date":277,"author_md5":261,"is_original":23,"collection":278,"summary_md5":279,"cover_url":280,"cover_url_1_1":281},132,"72360ca016a2d73c79a994732a6c9985","2024-11-09","#AI Code Generator","a9784420ab50b718dc3fe1ca40c467f8","article_res/cover/f331019b22da4c731e5cbb950f2151cf.jpeg","article_res/cover/e0236f165f8989e216a34876d6afead7.jpeg",{"id":283,"title_md5":284,"publish_date":285,"author_md5":286,"is_original":4,"collection":65,"summary_md5":287,"cover_url":288,"cover_url_1_1":289},545,"353cb37d21fcf40fd94d380751345349","2022-05-11","702f216f8493cff39e697e019495257e","5acb0305a6ca0b4effe61654d7364c1b","article_res/cover/d73e286a65a482df39f4e9a80f0a55b1.jpeg","article_res/cover/0695fd87a23b3e413a5a4d97e60fe3f6.jpeg",{"id":291,"title_md5":292,"publish_date":293,"author_md5":294,"is_original":4,"collection":5,"summary_md5":295,"cover_url":296,"cover_url_1_1":297},553,"40269effcd71f4ca2bccfa46103a02e4","2022-05-03","70997a2931a60561e615f5171df5f9a5","40f7fb7743cb3c2affc4257ecb713ec1","article_res/cover/2901b1d32f6e64a175a6c6ea65480f5f.jpeg","article_res/cover/0c886c8287ee075f45fa98b0fa976f00.jpeg",{"id":299,"title_md5":300,"publish_date":301,"author_md5":261,"is_original":23,"collection":302,"summary_md5":303,"cover_url":304,"cover_url_1_1":305},201,"800afd80aaddee713a42c090c127f2f9","2024-08-08","#AI Virtual Try-On","c78686846ebb44d0852dcfcfcf9aca0d","article_res/cover/ef225098873f65928409f51c6c85222a.jpeg","article_res/cover/748cc8a81d00aa968ea5ebb1172cb452.jpeg",{"id":307,"title_md5":308,"publish_date":309,"author_md5":261,"is_original":23,"collection":310,"summary_md5":311,"cover_url":312,"cover_url_1_1":313},351,"be689590d76ec63d2a5fa799058ac7b4","2024-01-04","#Tencent #AI Agent","ef991913a10b83e4e85fec169f91f75b","article_res/cover/6cbc4e6da87f70a4653a0103da6fea4e.jpeg","article_res/cover/21a5401f37fda9c0a18f9c02caffba20.jpeg",{"id":315,"title_md5":316,"publish_date":317,"author_md5":318,"is_original":4,"collection":319,"summary_md5":320,"cover_url":321,"cover_url_1_1":322},489,"79d450f17bcb17f8d94b54ce7a18ca0b","2023-04-05","9f3428c4d2d88afac6a16510d115e41c","#Stable Diffusion #AI Image Generator","6446a153259d4de8cd2fe72a21fb679c","article_res/cover/9a61cf0201b7b00ef497da3c846cdafb.jpeg","article_res/cover/957c0c5982eb2acf0114733f7c68df03.jpeg",{"related":324,"small":358},[325,326,334,342,350],{"id":144,"publish_date":145,"is_original":23,"collection":146,"cover_url":147,"cover_url_1_1":148,"title":149,"summary":150,"author":28},{"id":327,"publish_date":328,"is_original":23,"collection":329,"cover_url":330,"cover_url_1_1":331,"title":332,"summary":333,"author":28},52,"2025-02-01","#CUA #AI Agent","article_res/cover/4cdd14a75ebd0f2a2a0e5ac6255b1245.jpeg","article_res/cover/5e1606775fe81141ef0642d98338ea31.jpeg","Trial Browser-use: A new approach to local browser automation","Make websites accessible for AI agents",{"id":335,"publish_date":336,"is_original":4,"collection":337,"cover_url":338,"cover_url_1_1":339,"title":340,"summary":341,"author":28},277,"2024-05-12","#AI Index Report 2024 #Prompt Engineering #LLM","article_res/cover/6d277afc80e2551d0294bc3c6995b66a.jpeg","article_res/cover/c1ab171a5b7ca16284ee49b73ae116d2.jpeg","How to make large models smarter? \"The 2024 Artificial Intelligence Index Report\" - 2.12 LLM improvement techniques","As LLMs use increases, techniques are being sought to enhance their performance and efficiency.",{"id":343,"publish_date":344,"is_original":23,"collection":345,"cover_url":346,"cover_url_1_1":347,"title":348,"summary":349,"author":28},266,"2024-05-24","#LLM","article_res/cover/92f5039e1449570ba93aad47d06cfa43.jpeg","article_res/cover/47a3d09e7d099c9bb79adfe65a5c03a8.jpeg","LLM helps write complete reports","Try out STORM, where every search can be a brainSTORM",{"id":351,"publish_date":352,"is_original":23,"collection":353,"cover_url":354,"cover_url_1_1":355,"title":356,"summary":357,"author":28},56,"2025-01-28","#DeepSeek #MMM #AI Image Generator #Multimodal Understanding","article_res/cover/3b7efa559e0888141c890e933d504510.jpeg","article_res/cover/653880885ccb19b1ba9496f2aaee4a38.jpeg","DeepSeek Janus Series: Unified Multimodal Understanding and Generation Models","Janus-Series: Unified Multimodal Understanding and Generation Models",[359,365,371],{"title":10,"list":360},[361,362,363,364],{"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":366},[367,368,369,370],{"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":372},[],[8,9,10],[8,12,13,14,9,10,15,16,17,18],["Reactive",245],1754646417175]