[{"data":1,"prerenderedAt":205},["ShallowReactive",2],{"DlFXI4Eibt_Bn9lrEZz1TYbHCWFZj3IvqwHQSEW-Exc":3,"OhLfh4QkdZWiOq4oKp93NPXl5HhcQYIU4qQ7szgDR-I":194},{"code":4,"msg":5,"data":6},0,"",{"category":7,"tag":11,"hot":39,"new":78,"banner":118,"data":143,"cache":193},[8,9,10],"Agent","OpenAI","LLM",[12,14,17,20,23,25,27,30,33,36],{"title":8,"total":13},39,{"title":15,"total":16},"Google",44,{"title":18,"total":19},"Nvidia",13,{"title":21,"total":22},"Claude",11,{"title":9,"total":24},35,{"title":10,"total":26},85,{"title":28,"total":29},"DeepSeek",9,{"title":31,"total":32},"OCR",1,{"title":34,"total":35},"Chat",7,{"title":37,"total":38},"Generator",116,[40,48,55,64,71],{"id":41,"publish_date":42,"is_original":4,"collection":5,"cover_url":43,"cover_url_1_1":44,"title":45,"summary":46,"author":47},557,"2022-04-29","article_res/cover/7a9b1375ed9bb298154981bae42b794d.jpeg","article_res/cover/afa281dd52bc0454e6735daa8e6b0706.jpeg","Translation and summary of Messari Report [2.8 Kristin Smith, Blockchain Association and Katie Haun, a16z]","We need unity and speed right now.","Translation",{"id":49,"publish_date":50,"is_original":4,"collection":5,"cover_url":51,"cover_url_1_1":52,"title":53,"summary":54,"author":47},531,"2022-05-25","article_res/cover/e8362057f8fa189594c60afdfaaeb6e5.jpeg","article_res/cover/8ea08d0d6fa7eee6b57ed4ec61b61ad6.jpeg","Decentralized Society: Finding Web3’s Soul / Decentralized Society: Finding the Soul of Web3 -7","Decentralization through Pluralism When analyzing ecosystems, it's desirable to measure how decentralized it is.",{"id":56,"publish_date":57,"is_original":32,"collection":58,"cover_url":59,"cover_url_1_1":60,"title":61,"summary":62,"author":63},127,"2024-11-14","#Google #AI Game #World Model #AI Story","article_res/cover/0233a875b7ec2debf59779e311547569.jpeg","article_res/cover/6ffddb6ae4914b3c699493311aa9f198.jpeg","Google Launches \"Unbounded\": A Generative Infinite Character Life Simulation Game","Unbounded: A Generative Infinite Game of Character Life Simulation","Renee's Entrepreneurial Journey",{"id":13,"publish_date":65,"is_original":32,"collection":66,"cover_url":67,"cover_url_1_1":68,"title":69,"summary":70,"author":63},"2025-02-14","#Deep Dive into LLMs #Andrej Karpathy #LLM #Tool Use #Hallucination","article_res/cover/11e858ad6b74dfa80f923d549b62855c.jpeg","article_res/cover/615e1b320f1fc163edc1d2d154a6de33.jpeg","Andrej Karpathy's in-depth explanation of LLM (Part 4): Hallucinations","hallucinations, tool use, knowledge/working memory",{"id":72,"publish_date":73,"is_original":4,"collection":5,"cover_url":74,"cover_url_1_1":75,"title":76,"summary":77,"author":47},579,"2022-04-07","article_res/cover/39387376ba28447af1eb40576b9df215.jpeg","article_res/cover/02727ede8551ed49901d0abe6d6305b7.jpeg","Messari Report Translation and Summary 【1-7 Surviving the Winter】","I’d be more cautious here: 10 year and 10 hour thinking only.",[79,87,95,103,111],{"id":80,"publish_date":81,"is_original":32,"collection":82,"cover_url":83,"cover_url_1_1":84,"title":85,"summary":86,"author":63},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":88,"publish_date":89,"is_original":32,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":63},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":96,"publish_date":97,"is_original":32,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":63},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":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},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":112,"publish_date":105,"is_original":32,"collection":113,"cover_url":114,"cover_url_1_1":115,"title":116,"summary":117,"author":63},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",[119,127,135],{"id":120,"publish_date":121,"is_original":32,"collection":122,"cover_url":123,"cover_url_1_1":124,"title":125,"summary":126,"author":63},160,"2024-10-04","#Philosophy","article_res/cover/496990c49211e8b7f996b7d39c18168e.jpeg","article_res/cover/14dbaa1ade9cb4316d5829423a900362.jpeg","Time","The fungus of the morning does not know the waxing and waning of the moon, and the cicada does not know the seasons; this is a short life. To the south of the state of Chu there is a dark spirit which regards five hundred years as spring and five hundred years as autumn. In ancient times there was a great tree called the Ming which regarded eight thousand years as spring and eight thousand years as autumn; this is a long life.",{"id":128,"publish_date":129,"is_original":32,"collection":130,"cover_url":131,"cover_url_1_1":132,"title":133,"summary":134,"author":63},98,"2024-12-17","#AI Video Generator #Sora #Pika","article_res/cover/3b86e85d03fff4f356a3e4cf2bb329c9.jpeg","article_res/cover/5fa5c20ad0b40f8f544d257c0ef02938.jpeg","Pika 2.0 video generation officially released: effect comparison with Sora","今天，我们推出了Pika 2.0模型。卓越的文字对齐效果。惊人的视觉表现。还有✨场景成分✨",{"id":136,"publish_date":137,"is_original":32,"collection":138,"cover_url":139,"cover_url_1_1":140,"title":141,"summary":142,"author":63},71,"2025-01-14","#Nvidia #World Foundation Model #Cosmos #Physical AI #Embodied AI","article_res/cover/feddf8c832dfb45d28804291f6a42a9e.jpeg","article_res/cover/d6bc2f1186d96b78228c2283a17a3645.jpeg","NVIDIA's Cosmos World Model","Cosmos World Foundation Model Platform for Physical AI",[144,163,188],{"title":8,"items":145},[146,147,155],{"id":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},{"id":148,"publish_date":149,"is_original":32,"collection":150,"cover_url":151,"cover_url_1_1":152,"title":153,"summary":154,"author":63},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":156,"publish_date":157,"is_original":32,"collection":158,"cover_url":159,"cover_url_1_1":160,"title":161,"summary":162,"author":63},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",{"title":9,"items":164},[165,172,180],{"id":166,"publish_date":157,"is_original":32,"collection":167,"cover_url":168,"cover_url_1_1":169,"title":170,"summary":171,"author":63},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":173,"publish_date":174,"is_original":4,"collection":175,"cover_url":176,"cover_url_1_1":177,"title":178,"summary":179,"author":63},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":181,"publish_date":182,"is_original":4,"collection":183,"cover_url":184,"cover_url_1_1":185,"title":186,"summary":187,"author":63},417,"2023-08-24","#OpenAI","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.",{"title":10,"items":189},[190,191,192],{"id":88,"publish_date":89,"is_original":32,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":63},{"id":96,"publish_date":97,"is_original":32,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":63},{"id":104,"publish_date":105,"is_original":32,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":63},true,{"code":4,"msg":5,"data":195},{"id":196,"publish_date":197,"is_original":32,"collection":198,"articles_id":199,"cover_url":200,"cover_url_1_1":201,"title":202,"summary":203,"author":63,"content":204},222,"2024-07-10","#AI Avatar #Lip Sync #Tencent","5TbVJHqH7EUvozfZWewx0w","article_res/cover/d06d42c3261157730ffe4d634dbbae8a.jpeg","article_res/cover/4c134a6c9d3f5a35c0bda53ad9397af8.jpeg","Tencent MimicMotion: High-Quality Human Motion Video Generation Based on Confidence Pose Guidance","MimicMotion : High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","\u003Cdiv class=\"rich_media_content js_underline_content\n                       autoTypeSetting24psection\n            \" id=\"js_content\">\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>MimicMotion 能够生成任意长度的高质量视频，并模仿特定的运动引导。类似的项目之前介绍过很多：\u003C/span>\u003Cbr>\u003C/section>\u003Cul class=\"list-paddingleft-2\" style=\"list-style-type: disc;\">\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247489376&idx=1&sn=de5ed06770962462a49374dedfe8bf91&chksm=c13d13baf64a9aacd0e562774326f435e7abff51595d3156de987ce747289506f33574e8a476&scene=21#wechat_redirect\" textvalue=\"快手的LivePortrait - 视频驱动Avatar动画框架\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">快手的LivePortrait - 视频驱动Avatar动画框架\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247489178&idx=1&sn=66b6faf1ec9959452ad145c9278f31dc&chksm=c13d1240f64a9b56a7ece4b65bd0fb0d1015539d7937fe0a6faaf3cb659ee71b29e7ccb0679b&scene=21#wechat_redirect\" textvalue=\"MusePose和Follow-Your-Pose：腾讯发布的姿势驱动人物动作\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">MusePose和Follow-Your-Pose：腾讯发布的姿势驱动人物动作\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247488927&idx=1&sn=a706f31471bd0c8bbe5fb06ee46b2edb&chksm=c13d1145f64a985326ef70b246c0ce3e311f82c9c841e0bf5bd4fccbdd18e230fcbafc2b0641&scene=21#wechat_redirect\" textvalue=\"让 Avatar 动起来 - InstructAvatar、EMO、Follow-Your-Emoji\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">让 Avatar 动起来 - InstructAvatar、EMO、Follow-Your-Emoji\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247488926&idx=1&sn=b8c34b1660b9cd15d2a3c77993fd7ebf&chksm=c13d1144f64a9852aaaae90c4729e267289fcdecaa1962731ceb4185fc234d7acc17c6291fcb&scene=21#wechat_redirect\" textvalue=\"腾讯的两个让 Avatar 说话的模型：V-Express 和 MuseTalk\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">腾讯的两个让 Avatar 说话的模型：V-Express 和 MuseTalk\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247488924&idx=1&sn=7ca9212c451ab6fd3b6e6d126ee344e5&chksm=c13d1146f64a985095d4305386d6cdac8950e34de5db6e4a9cab1b9e06b67af7b17f90199ba6&scene=21#wechat_redirect\" textvalue=\"VASA-1 微软的逼真音频驱动的实时生成会话面孔\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">VASA-1 微软的逼真音频驱动的实时生成会话面孔\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247488209&idx=1&sn=7553b6dcbe5ff825da1e11c6ff36c6b3&chksm=c13d160bf64a9f1d76d59d3abc60ef4ec7b0c0433a5a0220f7ecf4700689cf1e17dd933418eb&scene=21#wechat_redirect\" textvalue=\"【Synthesia最新功能】表情丰富的虚拟人和语音克隆\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">【Synthesia最新功能】表情丰富的虚拟人和语音克隆\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247487736&idx=1&sn=12b99bfcf33982c06a9a356292d42f23&chksm=c13d1422f64a9d34f4bf1de9bd647a3fb3e939fa8926f5c124b9b7163c79b34b5390f632e157&scene=21#wechat_redirect\" textvalue=\"Rhubarb Lip Sync - AI 生成二次元角色的口型动画\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">Rhubarb Lip Sync - AI 生成二次元角色的口型动画\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247487709&idx=1&sn=4aa174705d31e6195d56ef5ae83c71c9&chksm=c13d1407f64a9d1101f80d0d51da4146760856037d042587f12118847063a085cf33bb59c07a&scene=21#wechat_redirect\" textvalue=\"Champ - 人体图像静态图片生成动画\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">Champ - 人体图像静态图片生成动画\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247487690&idx=1&sn=b33cedc3278337d11a7743ccd3fe0852&chksm=c13d1410f64a9d06f7e3fed6e18363d216086b3bfe423a30f41f7a6962b9db00a2b3dd2cde3d&scene=21#wechat_redirect\" textvalue=\"AniPortrait - 音频驱动的真实感肖像动画合成技术\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">AniPortrait - 音频驱动的真实感肖像动画合成技术\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247487027&idx=1&sn=85940f34a5834497022b325ec4fc3099&chksm=c13d0ae9f64a83ffd42318268dcef530594042a5db14b47a304a09b07436fa6ed6e5466db571&scene=21#wechat_redirect\" textvalue=\"阿里的DreaMoving：基于扩散模型的人物视频生成框架\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">阿里的DreaMoving：基于扩散模型的人物视频生成框架\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247486983&idx=1&sn=d059317d76ec29b1e1a838b0fadd72eb&chksm=c13d0addf64a83cb48886eb11781b395c019f2498bb1347580126b4995473bffbe65b5c6e7cc&scene=21#wechat_redirect\" textvalue=\"Meta 的 Audio2Photoreal - 从声音到虚拟人动起来\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">Meta 的 Audio2Photoreal - 从声音到虚拟人动起来\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247486443&idx=1&sn=a6f1ca9fe096793f0e4062d5ba81ec25&chksm=c13d0f31f64a8627553543c628d1c60fc319cb723dcc45a9f031ae08d2047bc18fa31fc10c64&scene=21#wechat_redirect\" textvalue=\"微软 GAIA：ZERO-SHOT的对口型单张图生成视频技术\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">微软 GAIA：ZERO-SHOT的对口型单张图生成视频技术\u003C/a>\u003C/span>\u003C/section>\u003C/li>\u003Cli>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247486443&idx=1&sn=a6f1ca9fe096793f0e4062d5ba81ec25&chksm=c13d0f31f64a8627553543c628d1c60fc319cb723dcc45a9f031ae08d2047bc18fa31fc10c64&scene=21#wechat_redirect\" textvalue=\"微软 GAIA：ZERO-SHOT的对口型单张图生成视频技术\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">\u003C/a>\u003Ca target=\"_blank\" href=\"http://mp.weixin.qq.com/s?__biz=MzkwOTMzMzk0MQ==&mid=2247485313&idx=1&sn=b36e78cef530b058c5e79ba82e0462a3&chksm=c13d035bf64a8a4d1081372e4f7cab990b6b3f4b9e1ddc71ffb5e017498c825d905b61571aa6&scene=21#wechat_redirect\" textvalue=\"使用 SadTalker 生成数字人视频\" linktype=\"text\" imgurl=\"\" imgdata=\"null\" data-itemshowtype=\"0\" tab=\"innerlink\" data-linktype=\"2\">使用 SadTalker 生成数字人视频\u003C/a>\u003C/span>\u003C/section>\u003Csection>\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003Cbr>\u003C/span>\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">本项目亮点：\u003C/span>\u003C/h2>\u003Cul style='margin-top: 8px;margin-bottom: 8px;;padding-left: 25px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);' class=\"list-paddingleft-1\">\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">引入了置信度姿态引导，确保了高帧质量和时间连续性。\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">引入了基于姿态置信度的区域损失放大，大大减少了图像失真。\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">为了生成长且平滑的视频，提出了一种渐进式潜在融合策略。\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Showcases\u003C/span>\u003C/h2>\u003Cul style='margin-top: 8px;margin-bottom: 8px;;padding-left: 25px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);' class=\"list-paddingleft-1\">\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">动作\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"https://res.cooltool.vip/article_res/assets/17423803228620.09890526070297567.mp4\" poster=\"https://res.cooltool.vip/article_res/assets/17423803228830.26105572006881506.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"https://res.cooltool.vip/article_res/assets/17423803228730.2561944745030338.mp4\" poster=\"https://res.cooltool.vip/article_res/assets/17423803228620.36108448711940966.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">跳舞\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"https://res.cooltool.vip/article_res/assets/17423803231580.5338827647271693.mp4\" poster=\"https://res.cooltool.vip/article_res/assets/17423803228610.1999275985634532.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"https://res.cooltool.vip/article_res/assets/17423803247280.6404522826052332.mp4\" poster=\"https://res.cooltool.vip/article_res/assets/17423803229490.942550891098054.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">说话\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"https://res.cooltool.vip/article_res/assets/17423803254640.07475771312154644.mp4\" poster=\"https://res.cooltool.vip/article_res/assets/17423803231960.06797127821691307.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"https://res.cooltool.vip/article_res/assets/17423803276170.24665159729769526.mp4\" poster=\"https://res.cooltool.vip/article_res/assets/17423803240430.5885379386022176.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\u003C/li>\u003C/ul>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003C/h2>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">试用\u003C/span>\u003C/h2>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>可以在 Replicate - https://replicate.com/zsxkib/mimic-motion 上运行 MimicMotion 进行试用。\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100005811\" data-ratio=\"1.5450180072028812\" data-s=\"300,640\" data-type=\"png\" data-w=\"833\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423803277870.612760515634504.png\">\u003C/p>\u003Cp>\u003Cbr>\u003C/p>\u003Cp>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">方法\u003C/span>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100005796\" data-ratio=\"0.5296296296296297\" data-type=\"png\" data-w=\"1080\" src=\"https://res.cooltool.vip/article_res/assets/17423803277870.37717322098916206.png\">\u003C/span>\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cstrong style=\";background: none 0% 0% / auto no-repeat scroll padding-box border-box rgba(0, 0, 0, 0);width: auto;height: auto;border-style: none;border-width: 3px;border-color: rgba(0, 0, 0, 0.4);border-radius: 0px;\">MimicMotion\u003C/strong> 结合了图像到视频的扩散模型和新颖的置信度姿态引导。模型的可训练组件包括一个时空 U-Net 和一个用于引入姿态序列作为条件的 PoseNet。置信度姿态引导的关键特性包括：\u003C/p>\u003Col style='margin-top: 8px;margin-bottom: 8px;;padding-left: 25px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);' class=\"list-paddingleft-1\">\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">姿态序列伴随着关键点置信度评分，使模型能够根据评分自适应地调整姿态引导的影响。\u003C/section>\u003C/li>\u003Cli style=\";\">\u003Csection style=\";margin-top: 5px;margin-bottom: 5px;color: rgb(1, 1, 1);line-height: 1.8em;letter-spacing: 0em;\">高置信度的区域在损失函数中赋予更大的权重，增强其在训练中的影响。\u003C/section>\u003C/li>\u003C/ol>\u003Ch3 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 20px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">置信度姿态引导\u003C/span>\u003C/h3>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>我们利用姿态引导帧的亮度来表示姿态估计的置信度。\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100005797\" data-ratio=\"0.6916666666666667\" data-type=\"jpeg\" data-w=\"1080\" src=\"https://res.cooltool.vip/article_res/assets/17423803277890.6739429611849039.jpeg\">\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>这种设计增强了生成对错误引导信号的鲁棒性（姿态 1&2），并提供了可见性提示以解决姿态模糊问题（姿态 3）。\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100005804\" data-ratio=\"0.6796296296296296\" data-type=\"jpeg\" data-w=\"1080\" src=\"https://res.cooltool.vip/article_res/assets/17423803280480.47282352836589014.jpeg\">\u003C/p>\u003Ch3 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 20px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">特定区域的手部细化\u003C/span>\u003C/h3>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>我们实施了一种基于置信度阈值生成掩码的策略。对于置信度评分超过预设阈值的区域，我们取消掩码，从而识别出可靠的区域。在计算视频扩散模型的损失时，相应于未遮蔽区域的损失值会被放大，使其在模型训练中比其他遮蔽区域更有效。\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>在相同的参考图像和姿态引导下，进行手部增强训练能够显著减少手部失真并提升视觉效果。\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100005805\" data-ratio=\"0.32407407407407407\" data-type=\"jpeg\" data-w=\"1080\" src=\"https://res.cooltool.vip/article_res/assets/17423803278730.5874999640941121.jpeg\">\u003C/p>\u003Ch3 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 20px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">渐进式潜在融合以实现时间平滑\u003C/span>\u003C/h3>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>我们提出了一种渐进式的方法来生成具有时间平滑效果的长视频。在每个去噪步骤中，视频片段首先在训练模型的条件下分别去噪，参考相同的图像和相应的姿态子序列。在每个去噪步骤中，图中用虚线框标记的重叠帧根据它们的位置逐步融合。\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100005798\" data-ratio=\"0.36203703703703705\" data-type=\"png\" data-w=\"1080\" src=\"https://res.cooltool.vip/article_res/assets/17423803278750.6216005818600536.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>渐进式潜在融合实现了平滑过渡，避免了视频片段边界的突然变化，从而增强了长视频生成的整体视觉时间一致性。\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100005806\" data-ratio=\"0.5462962962962963\" data-type=\"jpeg\" data-w=\"1080\" src=\"https://res.cooltool.vip/article_res/assets/17423803278740.5796953285876665.jpeg\">\u003C/p>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">对比\u003C/span>\u003C/h2>\u003Ch3 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 20px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">定性评估\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100005799\" data-ratio=\"0.3527777777777778\" data-type=\"jpeg\" data-w=\"1080\" src=\"https://res.cooltool.vip/article_res/assets/17423803290730.6813441687982833.jpeg\">\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100005800\" data-ratio=\"0.5777777777777777\" data-type=\"jpeg\" data-w=\"1080\" src=\"https://res.cooltool.vip/article_res/assets/17423803290830.36772871113213657.jpeg\">\u003C/span>\u003C/h3>\u003Ch3 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\";font-size: 20px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">定量评估\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100005802\" data-ratio=\"0.425\" data-s=\"300,640\" data-type=\"png\" data-w=\"800\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423803281710.9463144945598374.png\">\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100005803\" data-ratio=\"0.3679060665362035\" data-s=\"300,640\" data-type=\"png\" data-w=\"1022\" style=\"\" src=\"https://res.cooltool.vip/article_res/assets/17423803278770.8658113288148901.png\">\u003C/p>\u003C/span>\u003C/h3>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",1752585459553]