{"id":6024,"date":"2025-01-15T03:54:00","date_gmt":"2025-01-14T18:54:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6024"},"modified":"2025-01-15T03:54:00","modified_gmt":"2025-01-14T18:54:00","slug":"vita-1-5-towards-gpt-4o-level-real-time-vision-and-speech-interaction","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6024","title":{"rendered":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction\u00a0<\/strong>[104.4]<br>\u8996\u899a\u60c5\u5831\u3068\u97f3\u58f0\u60c5\u5831\u306e\u4e21\u65b9\u3092\u6bb5\u968e\u7684\u306b\u5b66\u7fd2\u3059\u308b\u591a\u6bb5\u968e\u5b66\u7fd2\u624b\u6cd5\u3092\u63d0\u6848\u3059\u308b\u3002 \u63d0\u6848\u624b\u6cd5\u306f, \u8996\u899a\u8a00\u8a9e\u80fd\u529b\u306e\u5f37\u5316\u3060\u3051\u3067\u306a\u304f, \u97f3\u58f0\u97f3\u58f0\u5bfe\u8a71\u306e\u52b9\u7387\u5411\u4e0a\u306b\u3082\u5bc4\u4e0e\u3059\u308b\u3002 \u753b\u50cf, \u30d3\u30c7\u30aa, \u97f3\u58f0\u30bf\u30b9\u30af\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306b\u304a\u3044\u3066, \u6211\u3005\u306e\u624b\u6cd5\u3092\u6700\u5148\u7aef\u306e\u624b\u6cd5\u3068\u6bd4\u8f03\u3059\u308b\u3053\u3068\u306b\u3088\u308a, \u30e2\u30c7\u30eb\u304c\u5f37\u3044\u8996\u899a\u3068\u97f3\u58f0\u306e\u4e21\u6a5f\u80fd\u3092\u5099\u3048\u3066\u3044\u308b\u3053\u3068\u3092\u793a\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2501.01957v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2501.01957v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 03 Jan 2025 18:59:52 GMT)<\/li>\n\n\n\n<li>Vision\u3068Speech\u306b\u5bfe\u5fdc\u3057\u305f\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u306a\u5bfe\u8a71\u30e2\u30c7\u30eb\u69cb\u7bc9\u306e\u305f\u3081\u30013\u6bb5\u968e\u3067\u306e\u5b66\u7fd2\u65b9\u6cd5\u3092\u63d0\u6848\u3002\u300cThe input side consists of vision and audio encoders, along with their adapters connected to a LLM. The output side has an end-to-end speech generation module, rather than directly using an external TTS model as the initial VITA-1.0 version\u300d\u3068\u3044\u3046\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u3002\u6027\u80fd\u306f\u516c\u958b\u30e2\u30c7\u30eb\u3084\u5546\u7528\u30e2\u30c7\u30eb\u3068\u7af6\u5408\u3059\u308b\u30ec\u30d9\u30eb\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/VITA-MLLM\/VITA\">GitHub &#8211; VITA-MLLM\/VITA: \u2728\u2728VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction<\/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":[251],"class_list":["post-6024","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-mllm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6024","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=6024"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6024\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6024"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6024"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6024"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}