{"id":273107,"date":"2026-06-14T23:00:00","date_gmt":"2026-06-15T03:00:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/06\/14\/hard-krypton-exclusive-interview-wang-zhongyuan-dean-of-beijing-academy-of-artificial-intelligence\/"},"modified":"2026-06-15T00:00:19","modified_gmt":"2026-06-15T04:00:19","slug":"hard-krypton-exclusive-interview-wang-zhongyuan-dean-of-beijing-academy-of-artificial-intelligence","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/06\/14\/hard-krypton-exclusive-interview-wang-zhongyuan-dean-of-beijing-academy-of-artificial-intelligence\/","title":{"rendered":"Hard Krypton Exclusive Interview: WANG Zhongyuan, Dean of Beijing Academy of Artificial Intelligence"},"content":{"rendered":"<p><a href=\"https:\/\/eu.36kr.com\/en\/p\/3853016586359817\">Hard Krypton Exclusive Interview: WANG Zhongyuan, Dean of Beijing Academy of Artificial Intelligence<\/a><\/p>\n<p><a href=\"https:\/\/eu.36kr.com\/en\/p\/3853016586359817\">https:\/\/eu.36kr.com\/en\/p\/3853016586359817<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-06-14 23:00:00<\/a><\/p>\n<p>Source Domain: <a href=\"eu.36kr.com\">eu.36kr.com<\/a><\/p>\n<p>Author | Qiu Xiaofen<\/p>\n<p>Editor | Yuan Silai<\/p>\n<p>In the past few months, the &#8220;World Model&#8221; has rapidly expanded from an academic jargon to a key term in the AI and robotics industries.<\/p>\n<p>Behind the industry&#8217;s focus lies real anxiety.<\/p>\n<p>On the one hand, after two years of wild growth, embodied intelligence has exposed the current shortcomings of AI in the physical world. Robots can recognize objects but don&#8217;t understand that &#8220;pushing a cup will make it fall&#8221;; they can understand instructions but can&#8217;t predict &#8220;how much force is needed to unscrew a bottle cap.&#8221; The world model aims to make up for this shortcoming, enabling robots to learn the laws and causality of the physical world.<\/p>\n<p>In other words, the relationship between the world model and embodied intelligence is essentially the relationship between the &#8220;brain&#8221; and the &#8220;body.&#8221;<\/p>\n<p>On the other hand, after exploring large language models, vision models, and multimodal models, large models need to move from the virtual world to the next stage in the real world.<\/p>\n<p>However, when capital, technology experts, and industrial resources are all poured into this area, people have no answer as to how the world model will truly be applied.<\/p>\n<p>In the view of Wang Zhongyuan, the director of the Beijing Academy of Artificial Intelligence (BAAI), the current global exploration of the world model is being torn into four distinct paths &#8211;<\/p>\n<p>The first type is the <strong>language &#8211; centered<\/strong> world model, including VLM and VLA. These models predict the next word in the text space and learn the world described by language but cannot understand the underlying physical consequences.<\/p>\n<p>The second type is the <strong>pixel &#8211; centered<\/strong> world model, such as video &#8211; generation models like Sora and Seedance. They learn videos or images in the visual space and learn the world described by pixels.<\/p>\n<p>The third type is the <strong>3D &#8211; structure &#8211; centered<\/strong> world model, including 3D reconstruction and the World Labs Marble model of Fei &#8211; Fei Li&#8217;s team. However, reconstructing a 3D space does not&#8230;<\/p>\n<p><a href=\"https:\/\/eu.36kr.com\/en\/p\/3853016586359817\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Hard Krypton Exclusive Interview: WANG Zhongyuan, Dean of Beijing Academy of Artificial Intelligence https:\/\/eu.36kr.com\/en\/p\/3853016586359817 Publish&#8230;<\/p>\n","protected":false},"author":1,"featured_media":273108,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/img.36krcdn.com\/hsossms\/20260614\/v2_887f92bc46f44e81b92571ae8c7068ee@000000_oswg25733oswg893oswg380_img_000?x-oss-process=image\/resize,m_mfit,w_600,h_400,limit_0\/crop,w_600,h_400,g_center","fifu_image_alt":"","footnotes":""},"categories":[14],"tags":[109],"class_list":["post-273107","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","tag-sora"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/273107"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=273107"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/273107\/revisions"}],"predecessor-version":[{"id":273109,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/273107\/revisions\/273109"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/273108"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=273107"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=273107"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=273107"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}