{"id":10287,"date":"2026-07-17T15:35:22","date_gmt":"2026-07-17T07:35:22","guid":{"rendered":"https:\/\/infernews.com\/blog\/acm-mm-2026-official-implementation-of-self-in-space-benchmarking-self-awareness\/"},"modified":"2026-07-17T15:35:22","modified_gmt":"2026-07-17T07:35:22","slug":"acm-mm-2026-official-implementation-of-self-in-space-benchmarking-self-awareness","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/acm-mm-2026-official-implementation-of-self-in-space-benchmarking-self-awareness\/","title":{"rendered":"Self-in-Space \u88dc\u4e0a\u7121\u4eba\u6a5f\u7a7a\u9593\u7406\u89e3\u76f2\u9ede"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/07\/pasted-6f5f393daae8.jpg\" alt=\"Teaser\"><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u8b1b\u7121\u4eba\u6a5f\u8996\u89ba\u7406\u89e3\uff0c\u5f88\u591a\u65b9\u6cd5\u96c6\u4e2d\u5728\u74b0\u5883\u8fa8\u8b58\u6216\u4efb\u52d9\u5b8c\u6210\uff0c\u4f46\u8f03\u5c11\u6b63\u9762\u8655\u7406\u98db\u884c\u5668\u672c\u8eab\u7684\u72c0\u614b\u611f\u77e5\u3002Self-in-Space\u5c6c\u65bc\u7814\u7a76\u578b\u57fa\u6e96\u6e2c\u8a66\u3001\u8a13\u7df4\u6578\u64da\u96c6\u8207\u6a21\u578b\u7d44\u5408\u9805\u76ee\uff0c\u6838\u5fc3\u662f\u628a UAV \u7684 spatial cognition \u8207 self-awareness \u5206\u958b\u6aa2\u67e5\uff0c\u770b\u770b\u6a21\u578b\u662f\u5426\u4e0d\u53ea\u300c\u898b\u5230\u7a7a\u9593\u300d\uff0c\u4ea6\u77e5\u9053\u81ea\u5df1\u5728\u5834\u666f\u4e2d\u5982\u4f55\u79fb\u52d5\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4f5c\u8005\u660e\u78ba\u6279\u8a55\u73fe\u6709 UAV-oriented MLLMs \u666e\u904d\u504f\u5411 environment-centered\u3001task-oriented \u7bc4\u5f0f\uff1a\u91cd\u8996\u5468\u570d\u6709\u4ec0\u9ebc\uff0c\u8f03\u5c11\u8655\u7406\u81ea\u8eab\u904b\u52d5\u5982\u4f55\u5f71\u97ff\u7406\u89e3\u3002\u70ba\u6b64\uff0c\u4ed6\u5011\u63d0\u51fa SIS-Bench\u3001SIS-Motion-54K \u8207 SIS-Motion\uff0c\u91cd\u65b0\u628a aerial understanding \u62c6\u6210 perception\u3001memory\u3001reasoning \u4e09\u5c64\uff0c\u518d\u540c\u6642\u8986\u84cb\u7a7a\u9593\u8207\u81ea\u6211\u5169\u689d\u8ef8\u7dda\uff0c\u4ee4\u554f\u984c\u5b9a\u7fa9\u6bd4\u4e00\u822c\u5f71\u7247\u554f\u7b54 benchmark \u66f4\u8cbc\u8fd1 embodied UAV \u5834\u666f\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">SIS-Bench \u5305\u542b 1,646 \u6bb5\u771f\u5be6 UAV \u5f71\u7247\u8207 4,856 \u7d44 QA\uff0c\u8986\u84cb 13 \u500b\u4efb\u52d9\uff1b\u5718\u968a\u7528\u5b83\u6e2c\u8a66 26 \u500b video MLLMs\uff0c\u5305\u62ec 6 \u500b proprietary models \u8207 20 \u500b open-source models\u3002\u7d50\u679c\u6307\u51fa\u5169\u500b\u7a69\u5b9a\u73fe\u8c61\uff1a\u6a21\u578b\u5c0d self \u7684\u5efa\u6a21\u5f31\u904e space\uff0c\u800c\u4e14\u80fd\u529b\u6703\u7531 perception \u8d70\u5230 memory\u3001\u518d\u5230 reasoning \u6642\u9010\u6b65\u4e0b\u8dcc\uff0c\u9019\u500b\u8a3a\u65b7\u6bd4\u55ae\u770b\u6574\u9ad4\u5206\u6578\u66f4\u6709\u53c3\u8003\u50f9\u503c\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u7d50\u5408 benchmark\u3001training dataset \u8207 motion-aware model\uff0c\u4e0d\u662f\u55ae\u4e00\u6a21\u578b\u767c\u4f48<\/li>\n<li>\u76f4\u63a5\u91dd\u5c0d UAV embodied intelligence \u7684 self-awareness \u7f3a\u53e3<\/li>\n<li>\u8a55\u6e2c\u8a2d\u8a08\u6709\u6e05\u695a\u5206\u5c64\uff0c\u65b9\u4fbf\u770b\u51fa\u6a21\u578b\u5728\u54ea\u4e00\u6bb5\u958b\u59cb\u5931\u6e96<\/li>\n<li>SIS-Motion \u5617\u8a66\u7528 motion-aware representation \u6539\u5584 aerial video understanding<\/li>\n<li>\u5df2\u516c\u958b SIS-Bench \u8207 SIS-Motion-54K\uff0c\u53ef\u5728 Hugging Face \u6216 ModelScope \u4e86\u89e3\u5167\u5bb9<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u9019\u9805\u76ee\u7684\u53d7\u773e\u5f88\u6e05\u695a\uff1a\u505a UAV \u8996\u89ba\u3001aerial video understanding\u3001embodied AI\u3001video MLLMs \u8a55\u6e2c\u7684\u4eba\uff0c\u90fd\u6703\u8f03\u5bb9\u6613\u7528\u5f97\u7740\u3002\u73fe\u968e\u6bb5\u5b83\u66f4\u50cf\u7814\u7a76\u8207\u6bd4\u8f03\u57fa\u790e\u8a2d\u65bd\uff0c\u800c\u4e0d\u662f\u5373\u88dd\u5373\u7528\u7522\u54c1\uff1b\u60f3\u90e8\u7f72\u6e2c\u8a66\uff0c\u8f03\u5408\u7406\u505a\u6cd5\u662f\u5148\u5f9e SIS-Bench \u9a57\u8b49\u73fe\u6709\u6a21\u578b\u5728 self-awareness \u8207 spatial reasoning \u7684\u8868\u73fe\uff0c\u518d\u770b SIS-Motion \u662f\u5426\u80fd\u70ba\u4e0b\u6e38 UAV navigation tasks \u5e36\u4f86\u53ef\u8f49\u79fb\u7684\u589e\u76ca\u3002\u76f8\u95dc\u6a21\u578b\u8207\u8cc7\u6e90\u4ee5 SIS-Motion\u3001SIS-Bench\u3001SIS-Motion-54K \u70ba\u4e3b\uff0c\u4e26\u4e14\u5c0d\u7167\u4e86\u591a\u500b video MLLMs \u7684\u8868\u73fe\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/choucisan.github.io\/publications\/self-in-space\/\" rel=\"noopener noreferrer\"><strong>\u9805\u76ee\u4e3b\u9801<\/strong><\/a> \u00b7 <a href=\"https:\/\/github.com\/IntelliSensing\/Self-in-Space\" rel=\"noopener noreferrer\"><strong>GitHub<\/strong><\/a> \u00b7 <a href=\"https:\/\/huggingface.co\/collections\/choucsan\/self-in-space\" rel=\"noopener noreferrer\"><strong>\u6a21\u578b<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u7121\u4eba\u6a5f\u7747\u5f97\u898b\u74b0\u5883\uff0c\u672a\u5fc5\u771f\u6b63\u7406\u89e3\u81ea\u5df1\u9ede\u6a23\u79fb\u52d5\u3002Self-in-Space\u628a\u8a55\u6e2c\u3001\u6578\u64da\u540c\u6a21\u578b\u653e\u57cb\u4e00\u9f4a\uff0c\u5c08\u9580\u62c6\u89e3\u5462\u500b\u843d\u5dee\u3002<\/p>\n","protected":false},"author":8,"featured_media":10286,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ai_generated_summary":"","footnotes":""},"categories":[133,185,176,140,31,119,127,196,199],"tags":[],"class_list":["post-10287","post","type-post","status-publish","format-standard","hentry","category-133","category-qwen","category-176","category-gemini","category-video","category-119","category-127","category-196","category-dataset-"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/10287","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=10287"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/10287\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/10286"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=10287"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=10287"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=10287"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}