{"id":6158,"date":"2025-02-14T04:56:00","date_gmt":"2025-02-13T19:56:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6158"},"modified":"2025-02-14T04:56:00","modified_gmt":"2025-02-13T19:56:00","slug":"physbench-benchmarking-and-enhancing-vision-language-models-for-physical-world-understanding","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6158","title":{"rendered":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding\u00a0<\/strong>[21.9]<br>\u8996\u899a\u8a00\u8a9e\u30e2\u30c7\u30eb(VLM)\u306f\u3001\u5e38\u8b58\u7684\u63a8\u8ad6\u306b\u304a\u3044\u3066\u512a\u308c\u3066\u3044\u308b\u304c\u3001\u7269\u7406\u4e16\u754c\u3092\u7406\u89e3\u3059\u308b\u306e\u306b\u82e6\u52b4\u3057\u3066\u3044\u308b\u3053\u3068\u3092\u793a\u3059\u3002 \u672c\u7a3f\u3067\u306f\u3001VLM\u306e\u4e00\u822c\u5316\u5f37\u5ea6\u3068\u30d3\u30b8\u30e7\u30f3\u30e2\u30c7\u30eb\u306e\u5c02\u9580\u77e5\u8b58\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bPhysAgent\u3092\u7d39\u4ecb\u3059\u308b\u3002 \u4ee5\u4e0a\u306e\u7d50\u679c\u304b\u3089,VLM\u306e\u7269\u7406\u4e16\u754c\u7406\u89e3\u80fd\u529b\u306e\u5411\u4e0a\u306f,Moka\u306a\u3069\u306e\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u5177\u4f53\u5316\u306b\u6709\u52b9\u3067\u3042\u308b\u3053\u3068\u304c\u793a\u5506\u3055\u308c\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2501.16411v2\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2501.16411v2\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 29 Jan 2025 03:52:39 GMT)<\/li>\n\n\n\n<li>VLM\u304c\u7269\u7406\u3092\u7406\u89e3\u3057\u3066\u3044\u308b\u304b\u3092\u6e2c\u308b\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3068Agentic\u306a\u00a0physical world understanding\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3001PhysAgent\u306e\u63d0\u6848\u3002<\/li>\n\n\n\n<li>\u73fe\u72b6\u306e\u7d50\u679c\u306f\u610f\u5916\u306a\u3053\u3068\u306b\uff08\uff1f\uff09 o1 > InternVL2.5-38B > InternVL2.5-78B > GPT-4o > Gemini-1.5-pro<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/physbench.github.io\/\">PhysBench<\/a>\u3001\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306f<a href=\"https:\/\/huggingface.co\/datasets\/USC-GVL\/PhysBench\">USC-GVL\/PhysBench \u00b7 Datasets at Hugging Face<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[449,517],"class_list":["post-6158","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-world-model","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6158","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6158"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6158\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6158"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6158"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6158"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}