{"id":6340,"date":"2025-10-15T10:29:03","date_gmt":"2025-10-15T02:29:03","guid":{"rendered":"https:\/\/nullthought.net\/?p=6340"},"modified":"2025-10-15T10:29:04","modified_gmt":"2025-10-15T02:29:04","slug":"paper2video%ef%bc%9a%e4%bb%8e%e8%ae%ba%e6%96%87%e8%87%aa%e5%8a%a8%e7%94%9f%e6%88%90%e5%ad%a6%e6%9c%af%e5%b1%95%e7%a4%ba%e8%a7%86%e9%a2%91","status":"publish","type":"post","link":"https:\/\/nullthought.net\/?p=6340","title":{"rendered":"Paper2Video\uff1a\u4ece\u8bba\u6587\u81ea\u52a8\u751f\u6210\u5b66\u672f\u5c55\u793a\u89c6\u9891"},"content":{"rendered":"\n<p>\u8bba\u6587<strong><a href=\"https:\/\/arxiv.org\/abs\/2510.05096\" target=\"_blank\" rel=\"noreferrer noopener\">Paper2Video: Automatic Video Generation from Scientific Papers<\/a><\/strong>\u63d0\u51fa\u4e86\u4e00\u4e2a\u9762\u5411\u5b66\u672f\u573a\u666f\u7684\u201c\u4ece\u8bba\u6587\u81ea\u52a8\u751f\u6210\u5b66\u672f\u5c55\u793a\u89c6\u9891\u201d\u65b9\u6848\uff1a\u57fa\u51c6\u6570\u636e\u96c6 Paper2Video\uff08101 \u7bc7\u8bba\u6587\u4e0e\u4f5c\u8005\u5f55\u5236\u7684\u5c55\u793a\u89c6\u9891\/\u5e7b\u706f\u7247\/\u8bf4\u8bdd\u4eba\u5143\u6570\u636e\u914d\u5bf9\uff09\uff0c\u4ee5\u53ca\u591a\u667a\u80fd\u4f53\u751f\u6210\u7cfb\u7edf PaperTalker\u3002\u4f5c\u8005\u540c\u65f6\u8bbe\u8ba1\u4e86\u56db\u7c7b\u9762\u5411\u201c\u5b66\u672f\u4f20\u64ad\u6709\u6548\u6027\u201d\u7684\u8bc4\u6d4b\u6307\u6807\uff08Meta Similarity\u3001PresentArena\u3001PresentQuiz\u3001IP Memory\uff09\uff0c\u5e76\u5728\u57fa\u51c6\u4e0a\u9a8c\u8bc1 PaperTalker \u7684\u6709\u6548\u6027\uff0c\u663e\u793a\u5176\u5728\u4fe1\u606f\u4f20\u8fbe\u4e0e\u53ef\u7528\u6027\u4e0a\u903c\u8fd1\u751a\u81f3\u5728\u90e8\u5206\u7ef4\u5ea6\u8d85\u8d8a\u4eba\u5de5\u5236\u4f5c\u7684\u89c6\u9891\u3002<\/p>\n\n\n\n<p>\u8bba\u6587\u4f5c\u8005\u4e3aZeyu Zhu, Kevin Qinghong Lin, Mike Zheng Shou\uff0c\u6765\u81eaNational University of Singapore\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"865\" height=\"265\" src=\"https:\/\/nullthought.net\/wp-content\/uploads\/2025\/10\/image-6.png\" alt=\"\" class=\"wp-image-6341\" srcset=\"https:\/\/nullthought.net\/wp-content\/uploads\/2025\/10\/image-6.png 865w, https:\/\/nullthought.net\/wp-content\/uploads\/2025\/10\/image-6-300x92.png 300w, https:\/\/nullthought.net\/wp-content\/uploads\/2025\/10\/image-6-768x235.png 768w\" sizes=\"auto, (max-width: 865px) 100vw, 865px\" \/><figcaption class=\"wp-element-caption\"><strong><a href=\"https:\/\/arxiv.org\/abs\/2510.05096\" target=\"_blank\" rel=\"noreferrer noopener\">Paper2Video: Automatic Video Generation from Scientific Papers<\/a><\/strong><\/figcaption><\/figure>\n\n\n\n<p>\u4e00\u3001\u4efb\u52a1\u5b9a\u4e49\u4e0e\u6838\u5fc3\u6311\u6218<br>\u4efb\u52a1\u8f93\u5165\u4e3a\uff1a\u8bba\u6587\u5168\u6587\uff08\u957f\u4e0a\u4e0b\u6587\u3001\u542b\u5927\u91cf\u56fe\u8868\u516c\u5f0f\uff09\u3001\u8bf4\u8bdd\u4eba\u8096\u50cf\u4e0e\u97f3\u8272\u6837\u672c\uff1b\u8f93\u51fa\u4e3a\uff1a\u53ef\u7528\u4e8e\u5b66\u672f\u6295\u7a3f\/\u4f1a\u8bae\u7684\u5b8c\u6574\u5c55\u793a\u89c6\u9891\uff08\u542b\u5b66\u672f\u98ce\u683c\u5e7b\u706f\u7247\u3001\u9010\u53e5\u5b57\u5e55\u4e0e\u8bed\u97f3\u3001\u8bf4\u8bdd\u4eba\u5934\u8bb2\u89e3\u753b\u9762\u3001\u5149\u6807\u6307\u5f15\uff09\u3002\u6311\u6218\u4e3b\u8981\u4f53\u73b0\u5728\uff1a<br>1\uff09\u591a\u6a21\u6001\u957f\u4e0a\u4e0b\u6587\u7406\u89e3\uff1a\u8bba\u6587\u901a\u5e38 20\u201330+ \u9875\u3001\u51e0\u5341\u5e45\u56fe\u8868\uff0c\u4fe1\u606f\u5bc6\u5ea6\u9ad8\u3002<br>2\uff09\u591a\u901a\u9053\u534f\u540c\u751f\u6210\u4e0e\u5bf9\u9f50\uff1a\u9700\u8981\u540c\u65f6\u534f\u8c03\u5e7b\u706f\u7247\u3001\u5b57\u5e55\u4e0e\u8bed\u97f3\u3001\u8bf4\u8bdd\u4eba\u89c6\u9891\u3001\u5149\u6807\u7684\u65f6\u7a7a\u4e00\u81f4\u6027\u3002<br>3\uff09\u4e2a\u6027\u5316\u8bf4\u8bdd\u4eba\u5408\u6210\uff1a\u5728\u4fdd\u8bc1\u8eab\u4efd\u5916\u89c2\u4e0e\u97f3\u8272\u4fdd\u771f\u7684\u540c\u65f6\u5b9e\u73b0\u7a33\u5b9a\u3001\u957f\u65f6\u7684\u5507\u52a8\u4e0e\u8868\u60c5\u3002<br>4\uff09\u65f6\u7a7a\u843d\u70b9\uff08grounding\uff09\uff1a\u5149\u6807\u9700\u8981\u4e0e\u8bed\u97f3\/\u5b57\u5e55\u8bed\u4e49\u540c\u6b65\uff0c\u5e76\u51c6\u786e\u843d\u5728\u5f53\u524d\u8981\u70b9\u533a\u57df\u4e0a\u3002<\/p>\n\n\n\n<p>\u4e8c\u3001Paper2Video \u57fa\u51c6\u4e0e\u6570\u636e\u7edf\u8ba1<br>\u6570\u636e\u6765\u6e90\u4e8e\u8fd1\u4e09\u5e74\u9876\u4f1a\uff08NeurIPS\/ICLR\/ICML\u3001CVPR\/ICCV\/ECCV\u3001ACL\/EMNLP\/NAACL \u7b49\uff09\u4f5c\u8005\u5f55\u5236\u7684\u5c55\u793a\u89c6\u9891\uff0c\u5e76\u5c3d\u53ef\u80fd\u914d\u9f50\u539f\u59cb PDF \u5e7b\u706f\u7247\u3001\u8bf4\u8bdd\u4eba\u8096\u50cf\u4e0e\u97f3\u9891\u6837\u672c\u3002\u5408\u8ba1 101 \u4e2a\u6837\u672c\uff0c\u5176\u4e2d\u7ea6 40% \u8fd8\u5305\u542b\u4f5c\u8005\u5e7b\u706f\u7247 PDF \u4ee5\u4fbf\u201c\u53c2\u8003\u5f0f\u201d\u8bc4\u6d4b\u3002\u7edf\u8ba1\u663e\u793a\uff1a\u5e73\u5747\u6bcf\u4e2a\u5c55\u793a\u7ea6 16 \u9875\u5e7b\u706f\u7247\u3001\u65f6\u957f\u7ea6 6 \u5206 15 \u79d2\uff1b\u8bba\u6587\u5e73\u5747 28.7 \u9875\u3001\u542b 44.7 \u5e45\u56fe\u300113.3k \u8bcd\uff083.3k tokens\uff09\u5de6\u53f3\uff0c\u8986\u76d6\u4e3b\u9898\u5e7f\u6cdb\u3002\u8be5\u57fa\u51c6\u5f3a\u8c03\u5bf9\u957f\u7a0b\u3001\u4ee3\u7406\u5f0f\uff08agentic\uff09\u4efb\u52a1\u7684\u8bc4\u6d4b\u4ef7\u503c\uff0c\u800c\u975e\u4ec5\u4ec5\u751f\u6210\u51e0\u79d2\u81ea\u7136\u89c6\u9891\u3002<\/p>\n\n\n\n<p>\u4e09\u3001\u8bc4\u6d4b\u4f53\u7cfb\uff08\u56db\u4e2a\u7ef4\u5ea6\uff09<br>1\uff09Meta Similarity\uff08\u201c\u50cf\u4e0d\u50cf\u4f5c\u8005\u7248\u672c\u201d\uff09\uff1a\u4ee5\u4eba\u7c7b\u89c6\u9891\u4e3a\u201c\u4f2a GT\u201d\uff0c\u6bd4\u8f83\u751f\u6210\u7684\u201c\u5e7b\u706f\u7247+\u5b57\u5e55\u201d\u4e0e\u4f5c\u8005\u7248\u672c\u7684\u4e00\u81f4\u6027\uff08VLM \u6253\u5206\uff09\uff0c\u8bed\u97f3\u76f8\u4f3c\u5ea6\u7528\u8bf4\u8bdd\u4eba\u5d4c\u5165\u7684\u4f59\u5f26\u76f8\u4f3c\u5ea6\u8861\u91cf\u3002<br>2\uff09PresentArena\uff08\u201c\u54ea\u4e2a\u66f4\u597d\u201d\uff09\uff1a\u4ee5 VideoLLM \u4f5c\u4e3a\u4ee3\u7406\u89c2\u4f17\uff0c\u53cc\u987a\u5e8f\u6210\u5bf9\u6bd4\u8f83\uff08A,B \u4e0e B,A\uff09\u4ee5\u524a\u5f31\u4f4d\u7f6e\u504f\u7f6e\uff0c\u7edf\u8ba1\u80dc\u7387\u3002<br>3\uff09PresentQuiz\uff08\u201c\u4f20\u8fbe\u4e86\u591a\u5c11\u8bba\u6587\u4fe1\u606f\u201d\uff09\uff1a\u7531\u8bba\u6587\u81ea\u52a8\u6784\u9020\u9009\u62e9\u9898\uff08\u542b\u7ec6\u8282\u4e0e\u9ad8\u5c42\u7406\u89e3\uff09\uff0c\u8ba9 VideoLLM \u4ec5\u57fa\u4e8e\u751f\u6210\u89c6\u9891\u4f5c\u7b54\uff0c\u51c6\u786e\u7387\u8d8a\u9ad8\u8868\u793a\u8986\u76d6\u8d8a\u597d\u3002<br>4\uff09IP Memory\uff08\u201c\u662f\u5426\u63d0\u5347\u4f5c\u8005\u4e0e\u5de5\u4f5c\u7684\u8bb0\u5fc6\u5ea6\/\u53ef\u89c1\u5ea6\u201d\uff09\uff1a\u6a21\u62df\u4f1a\u540e\u9047\u5230\u4f5c\u8005\u65f6\u80fd\u5426\u8054\u60f3\u5230\u76f8\u5173\u95ee\u9898\u7684\u80fd\u529b\uff0c\u6784\u9020\u8bf4\u8bdd\u4eba\u56fe\u7247\u4e0e\u77ed\u89c6\u9891\u7247\u6bb5+\u95ee\u9898\u914d\u5bf9\uff0c\u8ba9\u6a21\u578b\u4ece 4 \u4e2a\u5019\u9009\u4e2d\u5339\u914d\u51fa\u6b63\u786e\u95ee\u9898\uff0c\u51c6\u786e\u7387\u4e3a\u6307\u6807\u3002<\/p>\n\n\n\n<p>\u56db\u3001\u65b9\u6cd5\uff1aPaperTalker \u591a\u667a\u80fd\u4f53\u6d41\u6c34\u7ebf<br>\u6574\u4f53\u7531\u56db\u4e2a\u201cBuilder\u201d\u5e76\u884c\u534f\u4f5c\uff0c\u9762\u5411\u5b66\u672f\u5b9e\u7528\u6027\u800c\u975e\u7aef\u5230\u7aef\u6269\u6563\u751f\u6210\uff1a<br>1\uff09Slide Builder\uff08\u5b66\u672f\u98ce\u683c\u5e7b\u706f\u7247\u751f\u6210\u4e0e\u7248\u5f0f\u7ec6\u5316\uff09<br>\u2022 \u76f4\u63a5\u4ece\u8bba\u6587 LaTeX \u5de5\u7a0b\u751f\u6210 Beamer \u4ee3\u7801\uff08\u975e\u6a21\u677f\u53cd\u590d\u7f16\u8f91\uff09\uff0c\u7f16\u8bd1-\u8bca\u65ad-\u4fee\u590d\u95ed\u73af\uff0c\u786e\u4fdd\u8bed\u6cd5\u4e0e\u7ed3\u6784\u6b63\u786e\u3002<br>\u2022 \u63d0\u51fa\u201c\u6811\u641c\u7d22\u5f0f\u89c6\u89c9\u9009\u62e9\uff08Tree Search Visual Choice\uff09\u201d\u4f18\u5316\u7248\u5f0f\uff1a\u5bf9\u6613\u6ea2\u51fa\u7684\u9875\uff0c\u89c4\u5219\u5316\u5730\u679a\u4e3e\u5b57\u4f53\/\u56fe\u7f29\u653e\u7b49\u53c2\u6570\u2192\u6e32\u67d3\u5019\u9009\u2192\u7528 VLM \u8bc4\u5224\u9009\u62e9\u6700\u4f73\u5206\u652f\uff0c\u4ece\u800c\u7a33\u5b9a\u89e3\u51b3 overfull\u3001\u88c1\u5207\u7b49\u95ee\u9898\uff0c\u6bd4\u8ba9 LLM\u201c\u76f2\u8c03\u6570\u503c\u201d\u66f4\u53ef\u9760\u9ad8\u6548\u3002<br>2\uff09Subtitle Builder\uff08\u9010\u53e5\u811a\u672c\u4e0e\u89c6\u89c9\u5173\u6ce8\u63d0\u793a\uff09<br>\u2022 \u5c06\u6bcf\u9875\u5e7b\u706f\u7247\u6805\u683c\u5316\u9001\u5165 VLM\uff0c\u751f\u6210\u9010\u53e5\u5b57\u5e55 Ti \u53ca\u5bf9\u5e94\u7684\u89c6\u89c9\u5173\u6ce8\u63d0\u793a P\uff08\u63cf\u8ff0\u672c\u53e5\u5e94\u6307\u5411\u7684\u56fe\/\u6846\/\u9879\u76ee\u7b26\u53f7\u7b49\uff09\u3002<br>3\uff09Cursor Builder\uff08\u5149\u6807\u7684\u65f6-\u7a7a\u7ed1\u5b9a\uff09<br>\u2022 \u7a7a\u95f4\u5bf9\u9f50\uff1a\u57fa\u4e8e\u201c\u8ba1\u7b97\u673a\u4f7f\u7528\/GUI \u4ee3\u7406\u6a21\u578b\u201d\uff08\u5982 UI-TARS\uff09\u628a\u89c6\u89c9\u63d0\u793a P grounding \u4e3a\u5c4f\u5e55\u5750\u6807 (x,y)\u3002<br>\u2022 \u65f6\u95f4\u5bf9\u9f50\uff1a\u7528 WhisperX \u83b7\u5f97\u9010\u8bcd\u65f6\u95f4\u6233\uff0c\u4e0e\u53e5\u7ea7\u5b57\u5e55\u5bf9\u9f50\u5f97\u5230 (ts, te)\u3002<br>4\uff09Talker Builder\uff08\u4e2a\u6027\u5316\u58f0\u97f3\u4e0e\u8bf4\u8bdd\u4eba\u89c6\u9891\uff09<br>\u2022 \u8bed\u97f3\uff1a\u4ee5\u4f5c\u8005\u77ed\u97f3\u8272\u6837\u672c\u9a71\u52a8 TTS\uff08F5-TTS\uff09\uff0c\u9010\u9875\u5408\u6210\u81ea\u7136\u8bed\u97f3\u3002<br>\u2022 \u8bf4\u8bdd\u4eba\u89c6\u9891\uff1a\u4f7f\u7528 Hallo2\uff08\u4ec5\u5934\u90e8\uff09\u6216 FantasyTalking\uff08\u4e0a\u534a\u8eab\u52a8\u4f5c\uff09\uff0c\u5173\u952e\u662f\u201c\u6309\u9875\u5e76\u884c\u5408\u6210\u201d\uff0c\u5404\u9875\u72ec\u7acb\u3001\u5929\u7136\u5207\u573a\uff0c\u6574\u4f53\u901f\u5ea6 >6\u00d7\u3002<\/p>\n\n\n\n<p>\u4e94\u3001\u5b9e\u9a8c\u8bbe\u7f6e\u4e0e\u5bf9\u6bd4\u65b9\u6cd5<br>\u5bf9\u6bd4\u4e09\u7c7b\u57fa\u7ebf\uff1a<br>\u2022 \u7aef\u5230\u7aef\u81ea\u7136\u89c6\u9891\u6269\u6563\uff08\u5982 Wan2.2\u3001Veo3\uff09\uff1a\u4ece\u6587\u672c\u63d0\u793a\u76f4\u63a5\u751f\u6210\u77ed\u89c6\u9891\uff1b<br>\u2022 \u591a\u667a\u80fd\u4f53\u62fc\u63a5\uff08PresentAgent + PPTAgent\uff09\uff1a\u751f\u6210 PPT \u518d\u914d TTS \u65c1\u767d\uff0c\u4f46\u65e0\u4e2a\u6027\u5316\u8bf4\u8bdd\u4eba\uff0c\u4e14\u5b66\u672f\u5f00\u573a\/\u5927\u7eb2\u9875\u7b49\u98ce\u683c\u4e0d\u8db3\uff1b<br>\u2022 PaperTalker \u53ca\u5176\u53d8\u4f53\uff08\u53bb\u9664 Talker \/ \u53bb\u9664 Cursor \u7b49\uff09\u3002\u8bc4\u6d4b\u7528 GPT-4.1\uff08VLM\uff09\u4e0e Gemini-2.5-Flash\uff08VideoLLM\uff09\uff0c8\u00d7 RTX A6000 \u63a8\u7406\u3002<\/p>\n\n\n\n<p>\u516d\u3001\u4e3b\u8981\u7ed3\u679c<br>1\uff09Meta Similarity\uff1aPaperTalker \u5728\u201c\u8bed\u97f3\u76f8\u4f3c\u5ea6\u201d\u4e0e\u201c\u5185\u5bb9\u76f8\u4f3c\u5ea6\u201d\u5747\u6700\u9ad8\uff0c\u8868\u660e\u201c\u4e2a\u6027\u5316 TTS + Beamer \u751f\u6210 + \u6811\u641c\u7d22\u7248\u5f0f\u7ec6\u5316\u201d\u7684\u7ec4\u5408\u66f4\u8d34\u8fd1\u4eba\u7c7b\u4f5c\u54c1\u3002<br>2\uff09PresentArena\uff1a\u4e0e\u4f5c\u8005\u89c6\u9891\u6210\u5bf9\u6bd4\uff0cPaperTalker \u7684\u80dc\u7387\u5728\u5404\u6cd5\u4e2d\u6700\u9ad8\uff1b\u8fdb\u4e00\u6b65\u5bf9\u6bd4\u663e\u793a\uff0c\u52a0\u5165 Talker \u4e0e Cursor \u5206\u522b\u5e26\u6765\u611f\u77e5\u8d28\u91cf\u63d0\u5347\uff08\u65e0 Talker\/Cursor \u7684\u53d8\u4f53\u80dc\u7387\u4f4e 1.8%\uff09\u3002<br>3\uff09PresentQuiz\uff1a\u5728\u201c\u7ec6\u8282\u95ee\u7b54\u201d\u4e0e\u201c\u9ad8\u5c42\u7406\u89e3\u201d\u4e24\u7c7b\u9898\u578b\u4e0a\uff0cPaperTalker \u7684\u51c6\u786e\u7387\u4f18\u4e8e\u4eba\u7c7b\u7248\u672c\u4e0e PresentAgent\uff0c\u4e14\u7528\u66f4\u77ed\u65f6\u957f\u4f20\u9012\u4e86\u66f4\u591a\u6709\u6548\u4fe1\u606f\u3002\u5149\u6807\u5bf9 VideoLLM \u7684\u201c\u5b9a\u4f4d-\u7406\u89e3\u201d\u5c24\u4e3a\u6709\u76ca\u3002<br>4\uff09IP Memory\uff1aPaperTalker \u6700\u9ad8\uff0c\u8bf4\u660e\u201c\u5e26\u6709\u4f5c\u8005\u5916\u89c2\u4e0e\u97f3\u8272\u7684 Talker\u201d\u663e\u8457\u589e\u5f3a\u89c2\u4f17\u5bf9\u5de5\u4f5c\u7684\u8bb0\u5fc6\u951a\u70b9\u3002<br>5\uff09\u4eba\u7c7b\u4e3b\u89c2\u8bc4\u6d4b\uff1a\u4eba\u7c7b\u4f5c\u54c1\u5f97\u5206\u6700\u9ad8\uff0cPaperTalker \u6b21\u4e4b\uff0c\u663e\u8457\u4f18\u4e8e\u7aef\u5230\u7aef\u81ea\u7136\u89c6\u9891\u4e0e PresentAgent\uff0c\u63a5\u8fd1\u53ef\u76f4\u63a5\u4f7f\u7528\u7684\u8d28\u91cf\u95e8\u69db\u3002<\/p>\n\n\n\n<p>\u4e03\u3001\u6d88\u878d\u7814\u7a76\u4e0e\u53ef\u89e3\u91ca\u6027\u89c2\u5bdf<br>1\uff09Cursor \u7684\u4f5c\u7528\uff1a\u8bbe\u8ba1\u5b9a\u4f4d\u5f0f QA \u4efb\u52a1\uff0c\u6bd4\u8f83\u201c\u6709\/\u65e0\u5149\u6807\u201d\u6761\u4ef6\u4e0b VLM \u7684\u5b9a\u4f4d\u7b54\u9898\u51c6\u786e\u7387\uff1b\u5e26\u5149\u6807\u65f6\u51c6\u786e\u7387\u663e\u8457\u63d0\u5347\uff08\u65e0\u5149\u6807 0.084 \u2192 \u6709\u5149\u6807 0.633\uff09\uff0c\u9a8c\u8bc1\u5149\u6807\u5bf9\u201c\u6ce8\u610f\u529b\u5f15\u5bfc\u4e0e\u8bed\u4e49\u843d\u70b9\u201d\u7684\u5173\u952e\u4f5c\u7528\u3002<br>2\uff09\u6811\u641c\u7d22\u5f0f\u89c6\u89c9\u9009\u62e9\uff1a\u53bb\u9664\u8be5\u6a21\u5757\u663e\u8457\u964d\u4f4e\u201c\u8bbe\u8ba1\u8d28\u91cf\u201d\u8bc4\u5206\uff081\u20135 \u91cf\u8868\uff09\uff0c\u5c24\u5176\u5728\u89e3\u51b3 overfull\u3001\u88c1\u5207\u4e0e\u62e5\u6324\u5e03\u5c40\u4e0a\uff0c\u8be5\u6a21\u5757\u8d77\u5230\u51b3\u5b9a\u6027\u4f5c\u7528\u3002<\/p>\n\n\n\n<p>\u516b\u3001\u6548\u7387\u4e0e\u5de5\u7a0b\u6743\u8861<br>PaperTalker \u7684\u4ee3\u4ef7\u4e3b\u8981\u5728\uff1a\u4e00\u6b21\u6027\u751f\u6210 Beamer + \u8f7b\u91cf\u6811\u641c\u7d22\u7ec6\u5316 + \u5e76\u884c\u8bf4\u8bdd\u4eba\u751f\u6210\u3002\u4e0e\u201c\u4ea4\u4e92\u5f0f\u7f16\u8f91\u6a21\u677f\u201d\u7684\u65b9\u6cd5\u76f8\u6bd4\uff0cBeamer \u4ee3\u7801\u66f4\u7d27\u51d1\u3001Token \u6210\u672c\u66f4\u4f4e\uff1b\u5206\u9875\u5e76\u884c\u5c06\u89c6\u9891\u751f\u6210\u603b\u65f6\u957f\u964d\u5230\u975e\u5e76\u884c\u7684 ~1\/6\u3002\u5bf9\u6bd4 PresentAgent\uff0cPaperTalker \u5728 Token \u4e0e\u603b\u65f6\u95f4\/\u6210\u672c\u4e0a\u66f4\u5177\u53ef\u63a7\u6027\u4e0e\u53ef\u590d\u7528\u6027\u3002<\/p>\n\n\n\n<p>\u4e5d\u3001\u4e0e\u76f8\u5173\u5de5\u4f5c\u7684\u7cfb\u7edf\u6027\u6bd4\u8f83<br>\u2022 \u81ea\u7136\u89c6\u9891\u6269\u6563\uff08Veo3\u3001Wan2.2 \u7b49\uff09\u64c5\u957f\u77ed\u65f6\u3001\u5ba1\u7f8e\/\u8fd0\u52a8\u8fde\u8d2f\u6027\uff0c\u4f46\u5bf9\u201c\u957f\u6587\u6863\u6761\u4ef6\u3001\u6e05\u6670\u53ef\u8bfb\u6587\u672c\u3001\u591a\u56fe\u8de8\u9875\u5f15\u7528\u201d\u65e0\u80fd\u4e3a\u529b\uff0c\u4e14\u591a\u4e3a\u201c\u89c6\u9891+\u97f3\u4e50\/\u65c1\u767d\u201d\u7684\u677e\u8026\u5408\u3002<br>\u2022 PPT\/\u6d77\u62a5\u81ea\u52a8\u5316\uff08PPTAgent\u3001Paper2Poster\uff09\uff1a\u80fd\u505a\u201c\u9759\u6001\u6750\u6599\u201d\uff0c\u4f46\u96be\u4ee5\u7aef\u5230\u7aef\u8054\u52a8\u8bf4\u8bdd\u4eba\u3001\u5149\u6807\u4e0e\u5b57\u5e55\/\u8bed\u97f3\uff0c\u66f4\u7f3a\u4e4f\u5b66\u672f\u98ce\u683c\u7ec6\u8282\uff08\u5f00\u573a\u3001\u7eb2\u8981\u3001\u81f4\u8c22\u7b49\uff09\u3002<br>\u2022 PaperTalker \u5c06\u201c\u5b66\u672f\u4f20\u64ad\u7684\u56db\u8981\u7d20\u201d\u2014\u2014\u5e7b\u706f\u7247\u3001\u5b57\u5e55\/\u8bed\u97f3\u3001\u8bf4\u8bdd\u4eba\u3001\u5149\u6807\u2014\u2014\u5728\u4ee3\u7406\u6846\u67b6\u4e0b\u5f3a\u7ea6\u675f\u4e00\u81f4\u6027\uff0c\u5e76\u4ee5\u201c\u8bc4\u6d4b\u4f53\u7cfb\u201d\u95ed\u73af\u9a8c\u8bc1\u201c\u4f20\u9012\u5b66\u672f\u8981\u70b9\u201d\u7684\u80fd\u529b\u3002<\/p>\n\n\n\n<p>\u5341\u3001\u8bba\u6587\u7684\u5173\u952e\u521b\u65b0\u70b9<br>1\uff09\u4efb\u52a1\u4e0e\u57fa\u51c6\uff1a\u9996\u6b21\u7cfb\u7edf\u5b9a\u4e49\u201c\u8bba\u6587\u2192\u5b66\u672f\u5c55\u793a\u89c6\u9891\u201d\u7684\u4efb\u52a1\uff0c\u5e76\u7ed9\u51fa\u6210\u5bf9\u6570\u636e\u4e0e\u8bc4\u6d4b\u95ed\u73af\u3002<br>2\uff09\u8bc4\u6d4b\u7ef4\u5ea6\uff1a\u4ece\u201c\u50cf\u4e0d\u50cf\u4f5c\u8005\u7248\u672c\u201d\u201c\u89c2\u4f17\u504f\u597d\u201d\u201c\u4fe1\u606f\u4f20\u8fbe\u201d\u201c\u8bb0\u5fc6\u53ef\u89c1\u5ea6\u201d\u56db\u4e2a\u7ef4\u5ea6\u523b\u753b\u201c\u5b66\u672f\u4f20\u64ad\u8d28\u91cf\u201d\u3002<br>3\uff09\u6811\u641c\u7d22\u5f0f\u89c6\u89c9\u9009\u62e9\uff1a\u628a\u201c\u7248\u5f0f\u5fae\u8c03\u201d\u4ece\u201c\u8bed\u4e49\u7f16\u8f91\u201d\u89e3\u8026\u4e3a\u201c\u89c6\u89c9\u5019\u9009\u679a\u4e3e+VLM \u9009\u62e9\u201d\uff0c\u7a33\u5b9a\u3001\u53ef\u6269\u5c55\u3002<br>4\uff09\u5149\u6807\u65f6\u7a7a\u5bf9\u9f50\uff1a\u4ee5 GUI \u4ee3\u7406\u6a21\u578b + WhisperX \u5c06\u6bcf\u53e5\u843d\u70b9\u951a\u5b9a\u5728\u5173\u952e\u8981\u7d20\u4e0a\uff0c\u964d\u4f4e\u89c2\u4f17\u7684\u5916\u5728\u8ba4\u77e5\u8d1f\u8377\u3002<br>5\uff09\u5206\u9875\u5e76\u884c\u7684\u4e2a\u6027\u5316\u8bf4\u8bdd\u4eba\uff1a\u8d34\u5408\u771f\u5b9e\u5f55\u5236\u6d41\u7a0b\uff0c\u663e\u8457\u63d0\u9ad8\u751f\u6210\u901f\u5ea6\u4e0e\u5b9e\u7528\u6027\u95e8\u69db\u3002<\/p>\n\n\n\n<p>\u5341\u4e00\u3001\u5c40\u9650\u6027\u4e0e\u6f5c\u5728\u6539\u8fdb<br>1\uff09\u5bf9\u57fa\u7840\u6a21\u578b\u7684\u4f9d\u8d56\uff1a<a href=\"https:\/\/nullthought.net\/?p=4920\" target=\"_blank\" rel=\"noreferrer noopener\">VLM<\/a>\/VideoLLM \u7684\u5224\u65ad\u4e0e\u8bc4\u5206\u53ef\u80fd\u5e26\u6765\u201c\u6a21\u578b\u2014\u8bc4\u6d4b\u540c\u6e90\u504f\u5dee\u201d\u3002\u672a\u6765\u53ef\u589e\u52a0\u4eba\u5de5\u6807\u6ce8\u3001\u8de8\u6a21\u578b\u4ea4\u53c9\u8bc4\u6d4b\u4e0e\u5931\u914d\u9c81\u68d2\u6027\u5206\u6790\u3002<br>2\uff09\u9886\u57df\u6cdb\u5316\uff1a\u6570\u636e\u4ee5 AI \u9876\u4f1a\u4e3a\u4e3b\uff0c\u8de8\u5b66\u79d1\uff08\u533b\u5b66\u3001\u5316\u5b66\u3001\u793e\u4f1a\u79d1\u5b66\uff09\u7248\u5f0f\u4e0e\u53d9\u4e8b\u98ce\u683c\u53ef\u80fd\u9700\u4e13\u95e8\u9002\u914d\uff08\u56fe\u5f0f\u3001\u914d\u8272\u3001\u7b26\u53f7\u89c4\u8303\uff09\u3002<br>3\uff09\u4f26\u7406\u4e0e\u6388\u6743\uff1a\u8bf4\u8bdd\u4eba\u8096\u50cf\u4e0e\u97f3\u8272\u514b\u9686\u9700\u660e\u786e\u6388\u6743\u4e0e\u6c34\u5370\uff1b\u5efa\u8bae\u9ed8\u8ba4\u542f\u7528\u201c\u8eab\u4efd\u4f7f\u7528\u58f0\u660e\u201d\u201cAI \u751f\u6210\u6807\u8bc6\u201d\u3002<br>4\uff09\u591a\u8bed\u79cd\u4e0e\u53ef\u8fbe\u6027\uff1a\u5f53\u524d\u811a\u672c\u4e3a\u82f1\u6587\uff1b\u672a\u6765\u5e94\u8986\u76d6\u591a\u8bed\u8a00 TTS \u4e0e\u5b57\u5e55\u3001\u65e0\u969c\u788d\u89c4\u8303\uff08\u8272\u76f2\u8c03\u8272\u3001\u542c\u969c\u652f\u6301\uff09\u3002<br>5\uff09\u66f4\u957f\u65f6\u89c6\u9891\u7684\u8de8\u9875\u8fde\u8d2f\uff1a\u5206\u9875\u5e76\u884c\u4f1a\u727a\u7272\u8de8\u9875\u7684\u624b\u52bf\/\u59ff\u6001\u8fde\u7eed\u6027\uff0c\u53ef\u8003\u8651\u8f7b\u91cf\u7ea7\u8de8\u9875\u4e00\u81f4\u6027\u7ea6\u675f\u6216\u201c\u8f6f\u8f6c\u573a Talker\u201d\u3002<\/p>\n\n\n\n<p>\u5341\u4e8c\u3001\u5e94\u7528\u524d\u666f\u4e0e\u6269\u5c55\u8bbe\u60f3<br>\u2022 \u5b66\u672f\u751f\u4ea7\u529b\uff1a\u6295\u7a3f\u524d\u81ea\u52a8\u751f\u6210 2\u201310 \u5206\u949f\u89c6\u9891\uff1b\u8bfe\u7a0b\/\u7ec4\u4f1a\u53ef\u5feb\u901f\u751f\u6210\u8bb2\u89e3\u7248\u672c\uff1b\u7efc\u8ff0\/\u6559\u7a0b\u578b\u5185\u5bb9\u53ef\u534a\u81ea\u52a8\u6279\u91cf\u5316\u3002<br>\u2022 \u4ea7\u4e1a\/\u7814\u7a76\u4f20\u64ad\uff1a\u5c06\u6280\u672f\u767d\u76ae\u4e66\u3001\u4e13\u5229\u3001\u4f01\u4e1a\u7814\u7a76\u62a5\u544a\u81ea\u52a8\u8f6c\u5316\u4e3a\u8bb2\u89e3\u89c6\u9891\uff1b\u5bf9\u5927\u91cf\u6280\u672f\u6863\u6848\u5b9e\u73b0\u201c\u68c0\u7d22\u2192\u8bb2\u89e3\u201d\u7684\u6d41\u6c34\u7ebf\u3002<br>\u2022 \u4e0e\u5de5\u4e1a\u77e5\u8bc6\u5e93\/RAG \u7ed3\u5408\uff1a\u4ece\u7ed3\u6784\u5316\u77e5\u8bc6\u56fe\u4e0e\u6587\u6863\u8d44\u4ea7\u81ea\u52a8\u6c47\u603b\u8981\u70b9\uff0c\u751f\u6210\u201c\u5de5\u7a0b\u6c47\u62a5\u89c6\u9891\u201d\uff08\u542b\u5149\u6807\u6307\u5f15\u3001\u56fe\u8868\u6807\u6ce8\uff09\uff0c\u5e76\u53ef\u4e0e\u95ee\u7b54\u7cfb\u7edf\u8054\u52a8\u5f62\u6210\u201c\u770b\u2014\u95ee\u2014\u7b54\u201d\u7684\u4e92\u52a8\u95ed\u73af\u3002<\/p>\n\n\n\n<p>\u5341\u4e09\u3001\u590d\u73b0\u8981\u70b9\u4e0e\u5de5\u7a0b\u5efa\u8bae\uff08\u5b9e\u64cd\u89c6\u89d2\uff09<br>1\uff09\u8f93\u5165\u9884\u5904\u7406\uff1a\u4ece\u8bba\u6587 LaTeX \u5de5\u7a0b\u62bd\u53d6\u7ed3\u6784\uff08\u9898\u76ee\u3001\u4f5c\u8005\u3001\u6458\u8981\u3001\u7ae0\u8282\u3001\u56fe\u8868\uff09\uff0c\u4e3a Beamer \u751f\u6210\u63d0\u4f9b\u201c\u8bed\u4e49\u9aa8\u67b6\u201d\u3002<br>2\uff09Beamer \u4ee3\u7801\u6a21\u677f\u5316\uff1a\u51c6\u5907\u6700\u5c0f\u53ef\u7f16\u8bd1\u9aa8\u67b6\uff08\u4e3b\u9898\u3001\u5b57\u53f7\u3001\u9875\u811a\uff09\uff0c\u5c06\u7ae0\u8282\u6bb5\u843d\u6620\u5c04\u4e3a frame\/block\/itemize\uff1b\u7f16\u8bd1\u9519\u8bef\u8981\u6536\u96c6\u884c\u53f7\u4e0e\u544a\u8b66\uff08overfull\/underfull\uff09\u3002<br>3\uff09\u6811\u641c\u7d22\u7ec6\u5316\u7b56\u7565\uff1a\u5bf9\u542b\u56fe\u9875\u5148\u626b\u56fe\u7f29\u653e\uff08\u5982 1.25\/0.75\/0.5\/0.25\uff09\uff0c\u518d\u964d\u5b57\u4f53\uff1b\u6e32\u67d3\u56db\u5bab\u683c\u2192VLM \u5224\u522b\uff1b\u4fdd\u7559\u201c\u9009\u62e9\u7406\u7531\u201d\u4ee5\u4fbf\u53ef\u89e3\u91ca\u56de\u6eaf\u3002<br>4\uff09\u5b57\u5e55\u4e0e\u89c6\u89c9\u63d0\u793a\uff1aVLM \u9010\u9875\u751f\u6210 \u226450 \u8bcd\u811a\u672c\u4e0e\u201c\u6bcf\u53e5\u552f\u4e00\u5149\u6807\u63cf\u8ff0\u201d\uff1b\u907f\u514d\u8de8\u56fe\u6f02\u79fb\u3002<br>5\uff09\u5149\u6807\u843d\u70b9\uff1a\u7528 GUI \u4ee3\u7406\u6a21\u578b\u5c06\u201c\u63cf\u8ff0\u201d\u8f6c\u4e3a (x,y)\uff1b\u65f6\u95f4\u91c7\u7528 WhisperX \u5bf9\u9f50\u9010\u8bcd\u2014\u53e5\u7ea7\uff0c\u53e5\u5185\u5149\u6807\u4fdd\u6301\u9759\u6b62\uff0c\u53e5\u95f4\u79fb\u52a8\u3002<br>6\uff09\u4e2a\u6027\u5316\u8bed\u97f3\u4e0e Talker\uff1a\u9884\u91c7\u96c6 10\u201320 \u79d2\u9ad8\u4fe1\u566a\u97f3\u8272\u6837\u672c\uff1b\u957f\u89c6\u9891\u6309\u9875\u5e76\u884c\u5408\u6210\uff0c\u8f6c\u573a\u5904\u7edf\u4e00\u80cc\u666f\/\u6784\u56fe\uff0c\u5fc5\u8981\u65f6\u52a0\u8f7b\u91cf\u8fc7\u6e21\u3002<br>7\uff09\u5bfc\u51fa\u5408\u6210\uff1a\u5c06\u6bcf\u9875\uff08\u753b\u9762=\u5e7b\u706f\u7247+\u5149\u6807+Talker\uff09\u4e0e\u5bf9\u5e94\u97f3\u8f68\u62fc\u63a5\uff0c\u7edf\u4e00\u5206\u8fa8\u7387\u3001\u5e27\u7387\u4e0e\u7801\u7387\uff0c\u786e\u4fdd\u6587\u672c\u6e05\u6670\u5ea6\u4e0e\u538b\u7f29\u53cb\u597d\u3002<\/p>\n\n\n\n<p>\u5341\u56db\u3001\u7ed3\u8bba<br>Paper2Video \u7cfb\u7edf\u6027\u5730\u628a\u201c\u8bba\u6587\u2192\u53ef\u7528\u5b66\u672f\u5c55\u793a\u89c6\u9891\u201d\u4ece\u6982\u5ff5\u9a8c\u8bc1\u63a8\u8fdb\u5230\u201c\u5e26\u8bc4\u6d4b\u3001\u53ef\u590d\u73b0\u3001\u80fd\u843d\u5730\u201d\u7684\u9636\u6bb5\uff1bPaperTalker \u4ee5\u591a\u667a\u80fd\u4f53\u534f\u540c\u4e0e\u5de5\u7a0b\u5316\u7ea6\u675f\u5b9e\u73b0\u4e86\u9ad8\u4fe1\u606f\u5bc6\u5ea6\u3001\u5f3a\u5bf9\u9f50\u3001\u63a5\u8fd1\u5b9e\u7528\u8d28\u91cf\u7684\u89c6\u9891\u751f\u6210\uff0c\u5e76\u5728\u201c\u89c2\u4f17\u7406\u89e3\u4e0e\u8bb0\u5fc6\u201d\u4e24\u6761\u4e3b\u7ebf\u4e0a\u7ed9\u51fa\u660e\u786e\u53ef\u6bd4\u7684\u91cf\u5316\u6307\u6807\u3002\u8be5\u5de5\u4f5c\u4e3a\u201cAI4Research\u201d\u7684\u89c6\u9891\u5316\u4f20\u64ad\u5f00\u8f9f\u4e86\u65b0\u8def\u5f84\uff0c\u4e5f\u4e3a\u672a\u6765\u7684\u201c\u4ea4\u4e92\u5f0f\u8bba\u6587\u2014\u591a\u6a21\u6001\u8bb2\u89e3\u4f53\u201d\u5960\u5b9a\u4e86\u65b9\u6cd5\u4e0e\u8bc4\u6d4b\u57fa\u7840\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<p>Paper2Video\uff1a<a href=\"https:\/\/github.com\/showlab\/Paper2Video\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/github.com\/showlab\/Paper2Video<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u8bba\u6587Paper2Video: Automatic Video Generation from Scientif [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[8],"tags":[39,80],"class_list":["post-6340","post","type-post","status-publish","format-standard","hentry","category-tech","tag-ai","tag-cv"],"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"NullThought","author_link":"https:\/\/nullthought.net\/?author=1"},"rttpg_comment":0,"rttpg_category":"<a href=\"https:\/\/nullthought.net\/?cat=8\" rel=\"category\">Tech<\/a>","rttpg_excerpt":"\u8bba\u6587Paper2Video: Automatic Video Generation from Scientif&hellip;","_links":{"self":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/6340","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6340"}],"version-history":[{"count":1,"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/6340\/revisions"}],"predecessor-version":[{"id":6342,"href":"https:\/\/nullthought.net\/index.php?rest_route=\/wp\/v2\/posts\/6340\/revisions\/6342"}],"wp:attachment":[{"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6340"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6340"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nullthought.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6340"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}