機器人的健忘症有救了！阿里達摩院一口氣開源7個具身模型

機器人前瞻

02/11

業內首個擁有時空記憶的具身大腦基礎模型。作者 |許麗思編輯 |漠影機器人前瞻2月10日報道，今天，阿里巴巴達摩院發布並開源了具身智能大腦基礎模型RynnBrain。RynnBrain全系列共計7個模型，包含2B、8B、30B三種參數規模的RynnBrain基礎模型，以及針對特定場景的後訓練專有模型RynnBrain-Nav（導航）與RynnBrain-Plan-30B（規劃）等共計7個。其中，...

網頁鏈接

免責聲明：投資有風險，本文並非投資建議，以上內容不應被視為任何金融產品的購買或出售要約、建議或邀請，作者或其他用戶的任何相關討論、評論或帖子也不應被視為此類內容。本文僅供一般參考，不考慮您的個人投資目標、財務狀況或需求。TTM對信息的準確性和完整性不承擔任何責任或保證，投資者應自行研究並在投資前尋求專業建議。

熱議股票

{"basename":"/hant","ssrTDKData":{"titleTemplate":"%s - 老虎證券","title":"老虎证券全球投资理财平台| 一站式投资美股新股港股A股","description":"老虎证券助您一站式投资美股，新股，港股，A股等全球金融理财产品。新加坡华人最信赖的在线投资平台，现在加入即享低费用，24/5 无时差炒美股投资理财！","keywords":"老虎證券,老虎證券開戶,老虎券商,老虎證券官網,老虎證券app,tigertrade老虎證券,股票,炒股,新加坡股票交易平臺,投資,投資理財","social":{"ogDescription":"老虎证券助您一站式投资美股，新股，港股，A股等全球金融理财产品。新加坡华人最信赖的在线投资平台，现在加入即享低费用，24/5 无时差炒美股投资理财！","ogImage":"https://c1.itigergrowtha.com/portal5/static/media/og-logo.be62fbe1.png","ogUrl":"https://www.itiger.com/hant/news/2610931823"},"companyName":"老虎證券"},"pageData":{"isMobile":false,"isTiger":false,"isTTM":true,"region":"SGP","license":"TBSG","edition":"fundamental"},"isCrawlerRequest":true,"__swrFallback__":{"@#url:\"https://stock-news.skytigris.cn/v3/news\",params:#id:\"2610931823\",edition:\"fundamental\",auth_exemption:1,,,undefined,":{"share":"https://ttm.financial/m/news/2610931823?lang=zh_TW&edition=fundamental","thumbnail":"","is_english":false,"pubTime":"2026-02-11 19:25","share_image_url":"https://static.laohu8.com/9a95c1376e76363c1401fee7d3717173","id":"2610931823","market":"us","top_or_hot":-1,"title":"機器人的健忘症有救了！阿里達摩院一口氣開源7個具身模型","media":"機器人前瞻","content":"<div>\n<p>業內首個擁有時空記憶的具身大腦基礎模型。作者 |許麗思編輯 |漠影機器人前瞻2月10日報道，今天，阿里巴巴達摩院發布並開源了具身智能大腦基礎模型RynnBrain。RynnBrain全系列共計7個模型，包含2B、8B、30B三種參數規模的RynnBrain基礎模型，以及針對特定場景的後訓練專有模型RynnBrain-Nav（導航）與RynnBrain-Plan-30B（規劃）等共計7個。其中，...</p>\n\n<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260211192657a6eed20d&s=b\">網頁鏈接</a>\n\n</div>\n","source":"tencent","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>機器人的健忘症有救了！阿里達摩院一口氣開源7個具身模型</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 12.5px; color: #7E829C; margin: 0;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n機器人的健忘症有救了！阿里達摩院一口氣開源7個具身模型\n</h2>\n<h4 class=\"meta\">\n<p class=\"head\">\n<strong class=\"h-name small\">機器人前瞻</strong><span class=\"h-time small\">2026-02-11 19:25</span>\n</p>\n</h4>\n</header>\n<article>\n<div>\n<p>業內首個擁有時空記憶的具身大腦基礎模型。作者 |許麗思編輯 |漠影機器人前瞻2月10日報道，今天，阿里巴巴達摩院發布並開源了具身智能大腦基礎模型RynnBrain。RynnBrain全系列共計7個模型，包含2B、8B、30B三種參數規模的RynnBrain基礎模型，以及針對特定場景的後訓練專有模型RynnBrain-Nav（導航）與RynnBrain-Plan-30B（規劃）等共計7個。其中，...</p>\n\n<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260211192657a6eed20d&s=b\">網頁鏈接</a>\n\n</div>\n\n<div class=\"bt-text\">\n\n\n<p> 來源：<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260211192657a6eed20d&s=b\">機器人前瞻</a></p>\n<p>為提升您的閱讀體驗，我們對本頁面進行了排版優化</p>\n\n\n</div>\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"LU1267930227.SGD","symbol_name":"TEMPLETON GLOBAL BALANCED \"AS\" (SGD) ACC A","start_time":0,"source_url":"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260211192657a6eed20d&s=b","article_id":"2610931823","we_media_id":null,"thumbnails":[],"rights":{"source":"tencent","url":"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260211192657a6eed20d&s=b","rn_cache_url":null,"customStyle":"body{padding-top:10px;}#news_title{font-weight:bold;#titleStyle#;}#news_description span{font-size:12px;#descriptionStyle#;}.footer-note{#statement#}","selectors":".mod-LoadTzbdNews, body","filters":".relate-stock, .hot-list, .recom-box, .wx-sou","directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2610931823","pubTimestamp":1770809124,"columns":[],"sourceInfo":{"source_id":"tencent","name":"腾讯"},"weMediaInfo":null,"summary":"業內首個擁有時空記憶的具身大腦基礎模型。作者 |許麗思編輯 |漠影機器人前瞻2月10日報道，今天，阿里巴巴達摩院發布並開源了具身智能大腦基礎模型RynnBrain。RynnBrain還擁有良好的可拓展性，能夠快速後訓練出導航、規劃、動作等多種具身模型。▲RynnBrain具有認知、定位、推理、規劃等多重能力達摩院這次不僅開源了RynnBrain模型，而且配套開放了完整的推理訓練代碼。RynnBrain的出現，在一定程度上解決了具身模型在時空記憶與物理空間推理的短板。","collect":0,"end_time":0,"defaultTopTitle":"qq.com","property":[],"viewcount":null,"language":"zh","relate_stocks":{"LU1267930227.SGD":"TEMPLETON GLOBAL BALANCED \"AS\" (SGD) ACC A","LU1152091168.USD":"UBS (LUX) EQUITY FUND - CHINA OPPORTUNITY (USD) \"PM\" INC","LU1046422090.SGD":"Fidelity Pacific A-SGD","BABA":"阿里巴巴","BK4607":"DeepSeek概念股","LU0128525689.USD":"TEMPLETON GLOBAL BALANCED \"A\"(USD) ACC","LU0067412154.USD":"UBS (LUX) EQUITY FUND -  CHINA OPPORTUNITY \"P\" (USD) ACC","BK4220":"综合零售","LU0501845795.SGD":"瑞银大中华区股票基金P Acc SGD","BK4524":"宅经济概念","LU0052756011.USD":"TEMPLETON GLOBAL BALANCED \"A\" (USD) INC","BK4527":"明星科技股","LU1048596156.SGD":"Blackrock Asian Growth Leaders A2 SGD-H","BK4526":"热门中概股","LU1688375341.USD":"贝莱德中国灵活股票基金","LU1823568750.SGD":"Fidelity Global Technology A-ACC SGD","LU2148611432.USD":"AZ ALLOCATION BALANCED BRAVE \"AAZ\" (USDHDG) ACC","LU0797268264.HKD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AT\" (HKD) ACC","BK4122":"互联网与直销零售","BK4575":"芯片概念","IE00B0JY6N72.USD":"PINEBRIDGE GLOBAL EMERGING MARKETS FOCUS EQUITY \"A\" (USD) ACC","LU1235294995.USD":"FIDELITY GLOBAL TECHNOLOGY \"A\" (USDHDG) ACC","BK4614":"Manus概念股","BK4579":"人工智能","LU1769817096.USD":"UBS (LUX) EQUITY SICAV - GLOBAL EMERG MARKETS OPPO \"P\" (USD) INC","LU1282648689.USD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AMG\" (USD) INC","LU0348816934.USD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AT\" (USD)","LU1769817179.HKD":"UBS (LUX) EQUITY SICAV - GLOBAL EMERG MARKETS OPPO \"P\" (HKD) INC","LU0047713382.USD":"BGF EMERGING MARKETS \"A2\" ACC","BK4581":"高盛持仓","LU1051769294.HKD":"BGF EMERGING MARKETS EQUITY INCOME \"A6\"(HKDHDG) INC","BK4543":"AI","LU2226246903.HKD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AT4\" (HKD) ACC","BK4531":"中概回港概念","LU1152091754.HKD":"UBS (LUX) EQUITY FUND - CHINA OPPORTUNITY (USD) \"PM\" (HKD) INC","LU1048588211.SGD":"Blackrock Asian Dragon A2 SGD-H","BK4534":"瑞士信贷持仓","LU0072462343.USD":"贝莱德亚洲巨龙基金","LU0072913022.USD":"UBS (LUX) EQUITY FUND -  GREATER CHINA \"P\" (USD) ACC","BK4533":"AQR资本管理(全球第二大对冲基金)","LU1105468828.SGD":"Allianz Total Return Asian Equity AM DIS H2-SGD","BK4535":"淡马锡持仓","LU0651947912.USD":"BGF EMERGING MARKETS EQUITY INCOME \"A5G\" (USD) INC","BK4538":"云计算","LU0918141705.HKD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AM\" (HKD) INC","LU0106959298.USD":"UBS (LUX) EQUITY FUND - EMERGING MARKETS SUSTAINABLE LEADERS (USD) \"P\" (USD) ACC","LU1242518857.USD":"FULLERTON LUX FUNDS - ASIA ABSOLUTE ALPHA \"I\" (USD) ACC","LU0821914370.USD":"贝莱德亚洲成长领袖A2","BK4548":"巴美列捷福持仓","BABO":"BABA期权收益策略ETF-YieldMax","BK4554":"元宇宙及AR概念","BABW":"Roundhill BABA WeeklyPay ETF","LU0328353924.USD":"UBS (LUX) EQUITY SICAV - GLOBAL EMERGING MARKETS OPPORTUNITY (USD) \"P\" (USD) ACC","BABX":"2倍做多BABA ETF-GraniteShares","BK4585":"ETF&股票定投概念","LU0949170772.SGD":"Blackrock Global Equity Income A6 SGD-H","LU1003077747.HKD":"BGF GLOBAL EQUITY INCOME \"A6\" (HKDHDG) INC","IE00BF5LJ272.USD":"Legg Mason Martin Currie - Global Emerging Markets A Acc USD","BK4587":"ChatGPT概念","BK4558":"双十一","LU0880133367.SGD":"UBS (LUX) EQUITY FUND CHINA OPPORTUNITY USD \"P\" (SGD) ACC","LU0553294199.USD":"BGF GLOBAL EQUITY INCOME \"A5G\" (USD) INC","LU0918141887.USD":"安联亚洲实际收益股票基金","LU0738911758.USD":"Blackrock Global Equity Income A6 USD","LU0348814723.USD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"A\" (USD) INC  NC","09988":"阿里巴巴-W","BK4588":"碎股","IE00BFMHRM44.USD":"NEUBERGER BERMAN GLOBAL EQUITY MEGATRENDS \"A\" (USD) ACC","LU0251143458.SGD":"Fidelity Emerging Markets A-SGD","BK4565":"NFT概念","LU1046421795.USD":"富达环球科技A-ACC","BBYY":"GraniteShares YieldBOOST BABA ETF","LU0310800965.SGD":"FTIF - Templeton Global Balanced A Acc SGD","LU1242518931.SGD":"Fullerton Lux Funds - Asia Absolute Alpha A Acc SGD","LU0651946864.USD":"贝莱德新兴市场股票收益A2","LU1880383366.USD":"东方汇理中国股票基金 A2 (C)","LU1051768304.USD":"贝莱德新兴市场股票收益A6","KBAB":"2倍做多BABA ETF-KraneShares","LU0979878070.USD":"FULLERTON LUX FUNDS - ASIA ABSOLUTE ALPHA \"A\" (USD) ACC","BK4503":"景林资产持仓","LU1008478684.HKD":"UBS (LUX) EQUITY FUND -  CHINA OPPORTUNITY \"P\" (HKD) ACC","LU1515016050.SGD":"Blackrock Emerging Markets Equity Income A6 SGD-H","BK4502":"阿里概念","LU0456842615.SGD":"JPMorgan Funds - Emerging Markets Equity A (acc) SGD","BK4505":"高瓴资本持仓","LU0661504455.SGD":"Blackrock Global Equity Income A5 SGD-H","BK4504":"桥水持仓","LU0545039389.USD":"BGF GLOBAL EQUITY INCOME \"A2\" ACC"},"translate_title":"Amnesia of robots is saved! Alibaba Dharma Academy open source 7 embodied models in one go","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"ALBmain":0.6,"BBYY":0.6,"BABX":0.6,"KBAB":0.6,"BABA":1.91,"BABO":0.6,"09988":1.91,"BABW":0.6},"content_text":"業內首個擁有時空記憶的具身大腦基礎模型。作者 |許麗思編輯 |漠影機器人前瞻2月10日報道，今天，阿里巴巴達摩院發布並開源了具身智能大腦基礎模型RynnBrain。RynnBrain全系列共計7個模型，包含2B、8B、30B三種參數規模的RynnBrain基礎模型，以及針對特定場景的後訓練專有模型RynnBrain-Nav（導航）與RynnBrain-Plan-30B（規劃）等共計7個。其中，RynnBrain-30B-A3B是業界首個MoE具身基礎模型，其只需要3B的推理激活參數就全面超越了當前規模最大的具身基礎模型Palican-VL-72B，讓機器人動作更快、更絲滑。RynnBrain是業內首個擁有時空記憶的具身大腦基礎模型，引入了時空記憶和物理世界推理，讓機器人具有理解「時」與「空」的能力。簡單來説，就是機器人可以記得過去的軌跡，看懂現在的畫面，還能預判未來的動作，具有了全局時空回溯能力，減少了幻覺問題。比如，在雜亂的桌子面前，機器人正忙着給桌上的食物分類。突然，它收到了「請幫我拿一個麪包」的指令，選擇先停下手裏的動作，把麪包遞給人類。然後，它再轉頭處理啱啱的未完成的分類整理工作。在16項具身開源評測排行榜上，RynnBrain刷新了紀錄（SOTA），超越谷歌Gemini Robotics ER 1.5等行業頂尖模型。GitHub：https://github.com/alibaba-damo-academy/RynnBrain項目主頁：https://alibaba-damo-academy.github.io/RynnBrain.github.io/hugging face：https://huggingface.co/collections/Alibaba-DAMO-Academy/rynnbrain01.訓練速度提升兩倍，讓機器人擁有全局時空回溯能力RynnBrain在Qwen3-VL的基礎上訓練，還使用了自研的RynnScale架構對Dense模型和MOE模型進行訓練優化，能夠在同等資源下，訓練速度提升兩倍。同時，訓練數據超過2000萬對。▲RynnBrain模型架構RynnBrain能夠讓機器人實現堪比人類的全局時空回溯能力，關鍵在於做到了涵蓋空間、位置、事件、軌跡等多維度信息的統一表徵。其所構建的統一框架，能夠把機器人所接觸到的各種各樣的信息統一映射到模型的輸出空間裏，將時間維度、空間座標與語義理解融為一體。RynnBrain具有物理空間推理的能力，採用了一種全新的「文本與空間定位交錯」的推理策略，使得模型在推理時，不僅生成語言判斷，還會同步給出對應的空間指向信息。RynnBrain還擁有良好的可拓展性，能夠快速後訓練出導航、規劃、動作等多種具身模型。以具身規劃模型為例，其需要強大預測能力和場景解析能力，但基於RynnBrain，只需幾百條數據微調，效果就能超越Gemini 3 Pro，輕鬆實現SOTA。▲RynnBrain具有認知、定位、推理、規劃等多重能力達摩院這次不僅開源了RynnBrain模型，而且配套開放了完整的推理訓練代碼。另外，達摩院還開源了全新評測基準RynnBrain-Bench。這是一個用於評估具身理解能力的高維基準測試，從物體認知、空間認知、語義定位和指向交互四個核心維度全面評估模型性能，重點關注模型在連續視頻序列中對細粒度信息的理解能力與時空定位精度。02.實現了16個SOTA，超越谷歌、英偉達的具身頂尖模型結果顯示，RynnBrain，在16項具身開源評測排行榜上刷新紀錄（SOTA），包括環境感知與對象推理、第一人稱視覺問答、空間推理、軌跡預測等，超越了谷歌Gemini Robotics ER 1.5、英偉達 Cosmos Reason 2等具身頂尖模型。▲RynnBrain在16項具身評測上實現SOTA來看看模型在宇樹G1上的部署情況：在執行「把盤子放回原位」的任務時候，G1能夠準確識別盤子，並在盤子不停移動的情況下保持對其空間位置的記憶，具有物體記憶與空間記憶能力。面臨三個麪包分兩個盤子的難題時，機器人的空間規劃與長程規劃能力使它能找到合適的分配方法，把多出的一個麪包疊在中間。物體記憶能力與複雜視頻理解能力，使機器人能夠認出之前被喝過的礦泉水，並在複雜的變換中始終保持對物體的記憶。常識理解與中文OCR能力，讓機器人能夠根據用户「尋找低卡低糖的飲料」的需求，觀察瓶身的文字標籤，選擇出合適的飲料。03.結語：具身模型智能水平，已成為業內亟需解決的關鍵瓶頸目前，具身模型的智能水平成了行業發展的關鍵瓶頸，泛化能力亟待提升。業內主要探索兩條技術路線：一條是動作模型，以VLA模型為代表，能直接操控物理世界，但因數據稀缺，泛化能力不足；另一條是大腦模型，比如VLM模型，本身有一定泛化能力，卻缺少記憶、動態認知有限，還會出現物理認知偏差，無法支撐人形機器人完成複雜的移動與操作任務。RynnBrain的出現，在一定程度上解決了具身模型在時空記憶與物理空間推理的短板。達摩院不僅開源了RynnBrain模型，還配套開放了完整的推理訓練代碼、全新評測基準RynnBrain-Bench，為產業帶來了統一的基礎設施和評估標準，推動降低了具身智能領域的研發門檻。","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"symbols":[],"gpt_button":1,"need_auth":false,"code":"91000000","status":"200"}}}