{"id":7264,"date":"2026-01-09T23:30:50","date_gmt":"2026-01-09T15:30:50","guid":{"rendered":"https:\/\/infernews.com\/?p=7264"},"modified":"2026-01-09T23:30:52","modified_gmt":"2026-01-09T15:30:52","slug":"cov-%e6%8f%90%e5%8d%87%e8%a6%96%e8%a6%ba%e8%aa%9e%e8%a8%80%e7%9a%84%e7%a9%ba%e9%96%93%e6%8e%a8%e7%90%86%e8%83%bd%e5%8a%9b","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/cov-%e6%8f%90%e5%8d%87%e8%a6%96%e8%a6%ba%e8%aa%9e%e8%a8%80%e7%9a%84%e7%a9%ba%e9%96%93%e6%8e%a8%e7%90%86%e8%83%bd%e5%8a%9b\/","title":{"rendered":"CoV \u63d0\u5347\u8996\u89ba\u8a9e\u8a00\u7684\u7a7a\u9593\u63a8\u7406\u80fd\u529b"},"content":{"rendered":"\n

CoV<\/a> (Chain-of-View Prompting for Spatial Reasoning) \u53ef\u4ee5\u7528\u65bc\u5404\u7a2e\u9700\u8981\u5728\u8907\u96dc\u4e09\u7dad\u74b0\u5883\u4e2d\u9032\u884c\u7cbe\u78ba\u7a7a\u9593\u7406\u89e3\u7684\u5834\u666f\u3002\u4f8b\u5982 VR \u548c AR\uff0cCoV \u53ef\u4ee5\u5e6b\u52a9\u7cfb\u7d71\u66f4\u597d\u5730\u7406\u89e3\u548c\u97ff\u61c9\u7528\u6236\u5728\u865b\u64ec\u74b0\u5883\u4e2d\u7684\u67e5\u8a62\uff0c\u63d0\u4f9b\u66f4\u81ea\u7136\u3001\u66f4\u6c89\u6d78\u5f0f\u7684\u9ad4\u9a57\u3002\u5728\u81ea\u52d5\u99d5\u99db\u9818\u57df\uff0cCoV \u53ef\u4ee5\u589e\u5f37\u8eca\u8f1b\u5c0d\u5468\u570d\u74b0\u5883\u7684\u7406\u89e3\u80fd\u529b\uff0c\u63d0\u9ad8\u5176\u5728\u8907\u96dc\u9053\u8def\u689d\u4ef6\u4e0b\u7684\u5c0e\u822a\u548c\u6c7a\u7b56\u80fd\u529b\u3002<\/p>\n\n\n\n

CoV<\/a> \u63d0\u51fa\u4e00\u7a2e\u5275\u65b0\u65b9\u6cd5\uff0c\u5c08\u9580\u91dd\u5c0d\u5728\u4e09\u7dad\u74b0\u5883\u4e2d\u7684\u5177\u8eab\u554f\u7b54\uff08Embodied Question Answering, EQA\uff09\u554f\u984c\u3002\u50b3\u7d71\u7684\u8996\u89ba\u8a9e\u8a00\u6a21\u578b\uff08Vision-Language Models, VLMs\uff09\u53d7\u9650\u65bc\u56fa\u5b9a\u7684\u8f38\u5165\u8996\u89d2\uff0c\u9019\u4f7f\u5f97\u5b83\u5011\u5728\u63a8\u7406\u904e\u7a0b\u4e2d\u7121\u6cd5\u52d5\u614b\u5730\u7372\u53d6\u8207\u554f\u984c\u76f8\u95dc\u7684\u4e0a\u4e0b\u6587\u4fe1\u606f\uff0c\u9032\u800c\u9650\u5236\u4e86\u8907\u96dc\u7a7a\u9593\u63a8\u7406\u7684\u80fd\u529b\u3002CoV<\/a> \u901a\u904e\u5f15\u5165\u4e00\u7a2e\u514d\u8a13\u7df4\u3001\u50c5\u5728\u6e2c\u8a66\u968e\u6bb5\u904b\u884c\u7684\u6846\u67b6\u4f86\u89e3\u6c7a\u9019\u4e00\u554f\u984c\uff0c\u8a72\u6846\u67b6\u80fd\u5920\u8b93 VLMs \u8b8a\u6210\u4e3b\u52d5\u7684\u8996\u89d2\u63a8\u7406\u5668\u3002<\/p>\n\n\n\n

\"\"<\/a><\/figure>\n","protected":false},"excerpt":{"rendered":"

CoV (Chain-of-View Prompting for Spatial Reasoning) \u53ef\u4ee5\u7528\u65bc\u5404\u7a2e\u9700\u8981\u5728\u8907\u96dc\u4e09\u7dad\u74b0\u5883\u4e2d\u9032\u884c\u7cbe\u78ba\u7a7a\u9593\u7406\u89e3\u7684\u5834\u666f\u3002\u4f8b\u5982 VR \u548c AR\uff0cCoV \u53ef\u4ee5\u5e6b\u52a9\u7cfb\u7d71\u66f4\u597d\u5730\u7406\u89e3\u548c\u97ff\u61c9\u7528\u6236\u5728\u865b\u64ec\u74b0\u5883\u4e2d\u7684\u67e5\u8a62\uff0c\u63d0\u4f9b\u66f4\u81ea\u7136\u3001\u66f4\u6c89\u6d78\u5f0f\u7684\u9ad4\u9a57\u3002\u5728\u81ea\u52d5\u99d5\u99db\u9818\u57df\uff0cCoV \u53ef\u4ee5\u589e\u5f37\u8eca\u8f1b\u5c0d\u5468\u570d\u74b0\u5883\u7684\u7406\u89e3\u80fd\u529b\uff0c\u63d0\u9ad8\u5176\u5728\u8907\u96dc\u9053\u8def\u689d\u4ef6\u4e0b\u7684\u5c0e\u822a\u548c\u6c7a\u7b56\u80fd\u529b\u3002 CoV \u63d0\u51fa\u4e00\u7a2e\u5275\u65b0\u65b9\u6cd5\uff0c\u5c08\u9580\u91dd\u5c0d\u5728\u4e09\u7dad\u74b0\u5883\u4e2d\u7684\u5177\u8eab\u554f\u7b54\uff08Embodied Question Answering, EQA\uff09\u554f\u984c\u3002\u50b3\u7d71\u7684\u8996\u89ba\u8a9e\u8a00\u6a21\u578b\uff08Vision-Language Models, VLMs\uff09\u53d7\u9650\u65bc\u56fa\u5b9a\u7684\u8f38\u5165\u8996\u89d2\uff0c\u9019\u4f7f\u5f97\u5b83\u5011\u5728\u63a8\u7406\u904e\u7a0b\u4e2d\u7121\u6cd5\u52d5\u614b\u5730\u7372\u53d6\u8207\u554f\u984c\u76f8\u95dc\u7684\u4e0a\u4e0b\u6587\u4fe1\u606f\uff0c\u9032\u800c\u9650\u5236\u4e86\u8907\u96dc\u7a7a\u9593\u63a8\u7406\u7684\u80fd\u529b\u3002CoV \u901a\u904e\u5f15\u5165\u4e00\u7a2e\u514d\u8a13\u7df4\u3001\u50c5\u5728\u6e2c\u8a66\u968e\u6bb5\u904b\u884c\u7684\u6846\u67b6\u4f86\u89e3\u6c7a\u9019\u4e00\u554f\u984c\uff0c\u8a72\u6846\u67b6\u80fd\u5920\u8b93 VLMs \u8b8a\u6210\u4e3b\u52d5\u7684\u8996\u89d2\u63a8\u7406\u5668\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"googlesitekit_rrm_CAowvqSiDA:productID":"","footnotes":""},"categories":[185,149,133],"tags":[],"class_list":["post-7264","post","type-post","status-publish","format-standard","hentry","category-qwen","category-149","category-133"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/7264","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\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=7264"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/7264\/revisions"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=7264"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=7264"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=7264"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}