[{"data":1,"prerenderedAt":381},["ShallowReactive",2],{"$fgukOamtKU1RtUiMFsqdObttmqPPQz0uc7bl_gj_LyX0":3,"$fKLhVMLhrUiVAFGQb_U4eA3wMT207VOlZO-1_w7MSvz0":245,"article-321":380},{"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":322,"category":378,"tag":379},321,"2024-02-27","#Robotics","MtW9hoQ-BMxbxPdHOv1IIQ","article_res/cover/4f86f57341021b75b8ac791378cac8ac.jpeg","article_res/cover/109f2aaf82d772c9b463f8b29b447072.jpeg","Universal Manipulation Interface (UMI) - Unlocking powerful robot manipulation capabilities","We originally thought AI would help us wash dishes and clean the floor; then we'd have time to write poetry and paint. Now AI has started writing poetry and painting; but we're still washing dishes and cleaning the floor.","\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 read a paper titled \"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots.\" This research was conducted jointly by Stanford University, Columbia University, and the Toyota Research Institute.\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;'>It introduces a data collection and policy learning framework called the Universal Manipulation Interface (UMI), which enables skills directly acquired from in-the-wild human demonstrations to be transferred into deployable robot policies. UMI uses a handheld gripper combined with a carefully designed interface for portable, low-cost, and information-rich data collection suitable for challenging bimanual and dynamic manipulation demonstrations. To facilitate the learning of deployable policies, UMI incorporates a carefully designed policy interface with matched inference latency and relative trajectory action representation. The resulting learned policies are hardware-agnostic and can be deployed across multiple robot platforms. Equipped with these features, the UMI framework unlocks new robotic manipulation capabilities, enabling zero-shot generalization of dynamic, bimanual, precise, and long-horizon behaviors simply by changing the training data for each task. We demonstrate the versatility and effectiveness of UMI through comprehensive real-world experiments, showing that policies learned via UMI on trained human demonstrations can generalize zero-shot to new environments and objects.\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;'>For example, we have long awaited robots to wash dishes:\u003C/p>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423811436020.7154170283512962.mp4\" poster=\"./assets/17423811427010.6503857343426556.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\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;'>To successfully wash dishes, the robot must sequentially execute seven interdependent actions: turning on the faucet, grasping the plate, picking up the sponge, cleaning and wiping the plate until the ketchup is removed, placing the plate down, putting the sponge away, and turning off the faucet.\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;'>Hardware Design\u003C/h3>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003737\" data-ratio=\"0.2962962962962963\" data-s=\"300,640\" data-type=\"jpeg\" data-w=\"1080\" style=\"\" src=\"./assets/17423811437960.3651489814040396.jpeg\">\u003C/p>\u003Cp 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 data collection hardware of UMI uses a handheld parallel gripper with a GoPro camera mounted on it. To collect observation data usable for policy deployment, UMI needs to capture sufficient visual context to infer actions and acquire key information such as depth. To obtain action data leading to deployable policies, UMI needs to capture precise robot actions under fast human motions, fine-tune grip width, and automatically check whether each demonstration is valid under specific robot kinematic constraints.\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;'>With its unique wrist-mounted camera setup and camera-centric action representation, UMI achieves 100% calibration-free operation (even when the base moves) and can resist disturbances and drastic lighting changes.\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;'>UMI Policy Interface Design\u003C/h3>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003743\" data-ratio=\"0.3186915887850467\" data-s=\"300,640\" data-type=\"png\" data-w=\"1070\" style=\"\" src=\"./assets/17423811438030.2457732127099881.png\">\u003C/p>\u003Col class=\"list-paddingleft-1\" style=\"list-style-type: lower-alpha;\">\u003Cli>\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;'>We synchronize different streams of observational data using physically measured delays.\u003C/p>\u003C/li>\u003Cli>\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 UMI policy receives a sequence of synchronized observations (RGB images, relative end-effector (EE) poses, and gripper width) and outputs a sequence of desired relative end-effector poses and gripper widths as actions.\u003C/p>\u003C/li>\u003Cli>\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;'>We send action commands in advance to compensate for the robot's execution delay.\u003C/p>\u003C/li>\u003C/ol>\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;'>In-the-wild Generalization Experiments\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;'>With UMI, you can go to any home or restaurant and start collecting data within two minutes.\u003C/p>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423811430900.3894195447437858.mp4\" poster=\"./assets/17423811427120.003070137120651184.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\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;'>Using a diverse in-the-wild cup manipulation dataset, UMI enables us to train a diffusion policy that can generalize to extreme out-of-distribution objects and environments, including serving espresso cups above a water fountain!\u003C/p>\u003Csection>\u003Cdiv style=\"height: 508px; background: rgb(0, 0, 0); border-radius: 4px; overflow: hidden; margin-bottom: 12px;\">\u003Cvideo src=\"./assets/17423811432510.8338575018830543.mp4\" poster=\"./assets/17423811427030.546707966589109.jpeg\" controls=\"\" style=\"width: 100%;height: 100%;\">\u003C/video>\u003C/div>\u003C/section>\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;'>Narrow-Domain Evaluation Results\u003C/h3>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100003744\" data-ratio=\"0.6996197718631179\" data-s=\"300,640\" data-type=\"png\" data-w=\"1052\" style=\"\" src=\"./assets/17423811438360.832074846407435.png\">\u003C/p>\u003Col class=\"list-paddingleft-1\" style=\"list-style-type: lower-alpha;\">\u003Cli>\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;'>All initial states of the evaluation episodes are overlaid together.\u003C/p>\u003C/li>\u003Cli>\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;'>For each task, all methods start from the same set of initial states, which are manually matched via reference images.\u003C/p>\u003C/li>\u003Cli>\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;'>Typical failure modes of baseline/ablation policies. Red arrows indicate failure behaviors, green arrows indicate desired behaviors. Success rates over 20 evaluation episodes, with the best-performing entries in each column highlighted in bold.\u003C/p>\u003C/li>\u003C/ol>\u003Cp style=\"text-align: center;\">\u003Cbr>\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",[257,266,275,283,291,299,307,314],{"id":258,"title_md5":259,"publish_date":260,"author_md5":261,"is_original":4,"collection":262,"summary_md5":263,"cover_url":264,"cover_url_1_1":265},408,"9bc772a5c7613f1af36a3b13036a6c17","2023-09-21","bc27fa490c4d0d525bac812fc0793534","#AI Agents #LLM #AI Agent","55fbf3dbedcb325d132b0e8d22e03d77","article_res/cover/897f57a35c9bd3bb8e8c738dae940108.jpeg","article_res/cover/f83dfe7f16aef354ff7e6e1372afd074.jpeg",{"id":267,"title_md5":268,"publish_date":269,"author_md5":270,"is_original":4,"collection":271,"summary_md5":272,"cover_url":273,"cover_url_1_1":274},484,"af76b06a6a201755883f5b64a78911eb","2023-04-10","cfab1ba8c67c7c838db98d666f02a132","#Stable Diffusion #AI Image Generator","5d615395f499310d37a158d7addf51f7","article_res/cover/73624a211e1da591990a68332c54be3e.jpeg","article_res/cover/8d10285c2263513b4ec9b69fcc93a2c1.jpeg",{"id":276,"title_md5":277,"publish_date":278,"author_md5":261,"is_original":23,"collection":279,"summary_md5":280,"cover_url":281,"cover_url_1_1":282},38,"d82e55a5cbaea8662fa0629b90b563a5","2025-02-15","#AI Audio Generator #Sony","a86d13a74d78f7c7f2603b87e10c083b","article_res/cover/9162fca94aab5d1117b99c23c206dc87.jpeg","article_res/cover/c5731cc285b5bd55087f7243fc8bad46.jpeg",{"id":284,"title_md5":285,"publish_date":286,"author_md5":261,"is_original":4,"collection":287,"summary_md5":288,"cover_url":289,"cover_url_1_1":290},271,"f5ccdabe124301aa174c2564497debfb","2024-05-19","#LLM","70c64585e59d979a117552ddd3322831","article_res/cover/3a4eeb93d545f9ad15a06e987d1a3f14.jpeg","article_res/cover/0927f1e83e751e9b43eb30b9da0e3ca5.jpeg",{"id":292,"title_md5":293,"publish_date":294,"author_md5":295,"is_original":4,"collection":5,"summary_md5":296,"cover_url":297,"cover_url_1_1":298},571,"61bca3f1fd755515b5bfafda3f667c1e","2022-04-15","8b3607d0f4181a3cb6ffdccf7185f09b","a4e05af28e9fbed3c1ff2bbe106c505d","article_res/cover/ae56bce26e77b0fd07649773ef93454c.jpeg","article_res/cover/14e0a9222470370a4d81fb8562f19069.jpeg",{"id":300,"title_md5":301,"publish_date":302,"author_md5":261,"is_original":23,"collection":303,"summary_md5":304,"cover_url":305,"cover_url_1_1":306},9,"e76885f59103a7fe95322e5bdd9052a0","2025-03-12","#Mistral #OCR #le Chat","e1def0d3ef1b3afcba4b335ef17f4b9d","article_res/cover/301cdb65caf72bf97a07bae7506126be.jpeg","article_res/cover/9a111631ee196a9fab79ebe6bf35ed1d.jpeg",{"id":308,"title_md5":309,"publish_date":310,"author_md5":261,"is_original":4,"collection":5,"summary_md5":311,"cover_url":312,"cover_url_1_1":313},350,"36a5cbc3740f9c2e286121d0f06d001d","2024-01-04","9983c14b6502ea32f08f331c8539ba5c","article_res/cover/23db78c7ca1c23807770823e6522601d.jpeg","article_res/cover/fd73845afbf1b42d6259fa9df4354f89.jpeg",{"id":315,"title_md5":316,"publish_date":317,"author_md5":318,"is_original":4,"collection":5,"summary_md5":319,"cover_url":320,"cover_url_1_1":321},495,"9b15ccc6efafbde434556a70af4440d0","2023-03-30","9f3428c4d2d88afac6a16510d115e41c","8c3a91662be7ddf873148e266df78686","article_res/cover/9cc1e0b26ea462d3277b0d98b9a74620.jpeg","article_res/cover/8ecf7bdc377a506ebe83640c883cdff7.jpeg",{"related":323,"small":363},[324,331,339,347,355],{"id":325,"publish_date":326,"is_original":23,"collection":5,"cover_url":327,"cover_url_1_1":328,"title":329,"summary":330,"author":28},482,"2023-04-12","article_res/cover/3bc5b47ff3b06f43fe40a062c0fb8483.jpeg","article_res/cover/1add310252a4aab7eb875fe2ddd913f6.jpeg","【AIGC Learning】Use Google Colab to directly converse with ChatGPT - ChatGPT API Usage 1","GPT-4 will massively speed your ability to do these things, and with greater breadth and scope.  \n- Reid Hoffman",{"id":332,"publish_date":333,"is_original":23,"collection":334,"cover_url":335,"cover_url_1_1":336,"title":337,"summary":338,"author":28},5,"2025-03-15","#Meta #AI Video Generator","article_res/cover/6d289c936dcfa91f777ce3f553b01382.jpeg","article_res/cover/49d1007ac1b4cc08a3fa19c40455d915.jpeg","Meta's latest released video generation model VideoJAM","VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models",{"id":340,"publish_date":341,"is_original":4,"collection":5,"cover_url":342,"cover_url_1_1":343,"title":344,"summary":345,"author":346},607,"2022-03-10","article_res/cover/45e47d1f2bd97ea83773a8250da38e0e.jpeg","article_res/cover/e68da0da35ad8c14b37e94d666ed5e32.jpeg","How to read financial statements - Financial statements - \"Beginner's Guide\"","The reaction of weak management to weak operations is often weak accounting.","Course notes",{"id":348,"publish_date":349,"is_original":23,"collection":350,"cover_url":351,"cover_url_1_1":352,"title":353,"summary":354,"author":28},231,"2024-07-02","#Google #AI Code Generator #LLM","article_res/cover/101b4f136c9058c7fd14456adfec8935.jpeg","article_res/cover/e7eedf0d64b045dc540d773fc91cd2a8.jpeg","Gemma 2 is now available","Gemma2 offers best-in-class performance, runs at incredible speed across different hardware and easily integrates",{"id":356,"publish_date":357,"is_original":23,"collection":358,"cover_url":359,"cover_url_1_1":360,"title":361,"summary":362,"author":28},22,"2025-03-01","#AI Video Generation #Alibaba #Wan #StepFun #SkyReels","article_res/cover/cbb7d2892fdc47f5fe8d8c2972ced24e.jpeg","article_res/cover/db252440a3a3458792fd230884bc588a.jpeg","Several video generation models have been open-sourced recently.","Video Generative Models",[364,370,376],{"title":10,"list":365},[366,367,368,369],{"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":371},[372,373,374,375],{"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":377},[],[8,9,10],[8,12,13,14,9,10,15,16,17,18],["Reactive",245],1754646410656]