{"id":178496,"date":"2025-12-07T01:22:08","date_gmt":"2025-12-07T01:22:08","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/178496\/"},"modified":"2025-12-07T01:22:08","modified_gmt":"2025-12-07T01:22:08","slug":"this-ai-model-can-intuit-how-the-physical-world-works","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/178496\/","title":{"rendered":"This AI Model Can Intuit How the Physical World Works"},"content":{"rendered":"<p>The original version of <a href=\"https:\/\/www.quantamagazine.org\/how-one-ai-model-creates-a-physical-intuition-of-its-environment-20251003\/\" rel=\"nofollow noopener\" target=\"_blank\">this story<\/a> appeared in <a href=\"https:\/\/www.quantamagazine.org\" rel=\"nofollow noopener\" target=\"_blank\">Quanta Magazine<\/a>.<\/p>\n<p class=\"paywall\">Here\u2019s a test for infants: Show them a glass of water on a desk. Hide it behind a wooden board. Now move the board toward the glass. If the board keeps going past the glass, as if it weren\u2019t there, are they surprised? Many 6-month-olds are, and by a year, almost all children have an intuitive notion of an object\u2019s permanence, learned through observation. Now some artificial intelligence models do too.<\/p>\n<p class=\"paywall\">Researchers have developed an AI system that learns about the world via videos and demonstrates a notion of \u201csurprise\u201d when presented with information that goes against the knowledge it has gleaned.<\/p>\n<p class=\"paywall\">The model, created by Meta and called Video Joint Embedding Predictive Architecture (V-JEPA), does not make any assumptions about the physics of the world contained in the videos. Nonetheless, it can begin to make sense of how the world works.<\/p>\n<p class=\"paywall\">\u201cTheir claims are, a priori, very plausible, and the results are super interesting,\u201d says <a data-offer-url=\"https:\/\/www.uva.nl\/en\/profile\/h\/e\/m.heilbron\/m.heilbron.html\" class=\"external-link\" data-event-click=\"{&quot;element&quot;:&quot;ExternalLink&quot;,&quot;outgoingURL&quot;:&quot;https:\/\/www.uva.nl\/en\/profile\/h\/e\/m.heilbron\/m.heilbron.html&quot;}\" href=\"https:\/\/www.uva.nl\/en\/profile\/h\/e\/m.heilbron\/m.heilbron.html\" rel=\"nofollow noopener\" target=\"_blank\">Micha Heilbron<\/a>, a cognitive scientist at the University of Amsterdam who studies how brains and artificial systems make sense of the world.<\/p>\n<p>Higher Abstractions<\/p>\n<p class=\"paywall\">As the engineers who build self-driving cars know, it can be hard to get an AI system to reliably make sense of what it sees. Most systems designed to \u201cunderstand\u201d videos in order to either classify their content (\u201ca person playing tennis,\u201d for example) or identify the contours of an object\u2014say, a car up ahead\u2014work in what\u2019s called \u201cpixel space.\u201d The model essentially treats every pixel in a video as equal in importance.<\/p>\n<p class=\"paywall\">But these pixel-space models come with limitations. Imagine trying to make sense of a suburban street. If the scene has cars, traffic lights and trees, the model might focus too much on irrelevant details such as the motion of the leaves. It might miss the color of the traffic light, or the positions of nearby cars. \u201cWhen you go to images or video, you don\u2019t want to work in [pixel] space because there are too many details you don\u2019t want to model,\u201d said <a href=\"https:\/\/vivo.brown.edu\/display\/rbalestr\" target=\"_blank\" rel=\"nofollow noopener\">Randall Balestriero<\/a>, a computer scientist at Brown University.<\/p>\n<p><img decoding=\"async\" alt=\"Image may contain Yann LeCun Face Happy Head Person Smile Photography Portrait Dimples Adult and Accessories\" loading=\"lazy\" class=\"ResponsiveImageContainer-eNxvmU cfBbTk responsive-image__image\"   src=\"https:\/\/www.newsbeep.com\/ie\/wp-content\/uploads\/2025\/12\/Yann_LeCun-cr-Ecole-polytechnique-Universite-Paris-Saclay.jpeg\"\/><\/p>\n<p>Yann LeCun, a computer scientist at New York University and the director of AI research at Meta, created JEPA, a predecessor to V-JEPA that works on still images, in 2022.<\/p>\n<p>Photograph: E\u0301cole Polytechnique Universite\u0301 Paris-Saclay<\/p>\n","protected":false},"excerpt":{"rendered":"The original version of this story appeared in Quanta Magazine. Here\u2019s a test for infants: Show them a&hellip;\n","protected":false},"author":2,"featured_media":178497,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[220,218,219,61,60,18290,82,80],"class_list":{"0":"post-178496","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-ie","12":"tag-ireland","13":"tag-quanta-magazine","14":"tag-science","15":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/178496","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=178496"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/178496\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/178497"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=178496"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=178496"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=178496"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}