小鹏联合北大提出全新视觉Token剪枝框架，何小鹏：在探索L4路上又取得新突破

新浪科技2025-12-28

新浪科技讯 12月28日下午消息，近日，人工智能领域国际会议AAAI 2026公布了论文录用结果，由小鹏汽车和北京大学计算机学院多媒体信息处理全国重点实验室联合完成的论文《FastDriveVLA： Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning》成功入选。这篇论文最大的贡献在于，...

网页链接

免责声明：本文观点仅代表作者个人观点，不构成本平台的投资建议，本平台不对文章信息准确性、完整性和及时性做出任何保证，亦不对因使用或信赖文章信息引发的任何损失承担责任。

精彩评论

我们需要你的真知灼见来填补这片空白

发表看法

{"i18n":{"language":"zh_CN"},"isChannel":false,"data":{"share":"https://www.laohu8.com/m/news/2594221852?lang=zh_CN&edition=full","thumbnail":"","is_english":false,"pubTime":"2025-12-28 15:56","share_image_url":"https://static.laohu8.com/b0d1b7e8843deea78cc308b15114de44","id":"2594221852","market":"fut","top_or_hot":-1,"title":"小鹏联合北大提出全新视觉Token剪枝框架，何小鹏：在探索L4路上又取得新突破","media":"新浪科技","content":"<div>\n<p>新浪科技讯 12月28日下午消息，近日，人工智能领域国际会议AAAI 2026公布了论文录用结果，由小鹏汽车和北京大学计算机学院多媒体信息处理全国重点实验室联合完成的论文《FastDriveVLA： Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning》成功入选。这篇论文最大的贡献在于，...</p>\n\n<a href=\"https://finance.sina.com.cn/tob/2025-12-28/doc-inheivtn8742448.shtml\">网页链接</a>\n\n</div>\n","source":"sina","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>小鹏联合北大提出全新视觉Token剪枝框架，何小鹏：在探索L4路上又取得新突破</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n小鹏联合北大提出全新视觉Token剪枝框架，何小鹏：在探索L4路上又取得新突破\n</h2>\n\n<h4 class=\"meta\">\n\n\n2025-12-28 15:56 北京时间&nbsp;&nbsp;&nbsp;<a href=https://finance.sina.com.cn/tob/2025-12-28/doc-inheivtn8742448.shtml><strong>新浪科技</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>新浪科技讯 12月28日下午消息，近日，人工智能领域国际会议AAAI 2026公布了论文录用结果，由小鹏汽车和北京大学计算机学院多媒体信息处理全国重点实验室联合完成的论文《FastDriveVLA： Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning》成功入选。这篇论文最大的贡献在于，...</p>\n\n<a href=\"https://finance.sina.com.cn/tob/2025-12-28/doc-inheivtn8742448.shtml\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"09868","symbol_name":"小鹏汽车-W","start_time":0,"source_url":"https://finance.sina.com.cn/tob/2025-12-28/doc-inheivtn8742448.shtml","article_id":"2594221852","we_media_id":null,"thumbnails":[],"rights":null,"url":"https://stock-news.laohu8.com/highlight/detail?id=2594221852","pubTimestamp":1766908560,"columns":[],"sourceInfo":{"source_id":"sina","name":"sina"},"weMediaInfo":null,"summary":"新浪科技讯 12月28日下午消息，近日，人工智能领域国际会议AAAI 2026公布了论文录用结果，由小鹏汽车和北京大学计算机学院多媒体信息处理全国重点实验室联合完成的论文《FastDriveVLA： Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning》成功入选。这篇论文最大的贡献在于，提出了一种专门为端到端自动驾驶VLA模型定制的、高效的视觉Token剪枝框架——FastDriveVLA。","collect":0,"end_time":0,"defaultTopTitle":"sina.com.cn","property":[],"viewcount":null,"language":"zh","relate_stocks":{"09868":"小鹏汽车-W","BK4555":"新能源车","BK1575":"同股不同权","EVS.SI":"MSCI China Electric Vehicles and Future Mobility ETF-NikkoAM","BK4551":"寇图资本持仓","BK4526":"热门中概股","BK1119":"汽车制造商","XPEV":"小鹏汽车","BK4505":"高瓴资本持仓","BK1610":"ETF&股票定投概念","BK4099":"汽车制造商","BK1587":"次新股","LU0593848301.USD":"未来资产亚洲卓越消费股票基金A","BK1539":"汽车股","BK1588":"回港中概股"},"translate_title":"XPeng and Peking University proposed a new visual Token pruning framework. He XPeng: Another new breakthrough has been made on the road to exploring L4","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"09868":1.91,"EVS.SI":0.6,"XPEV":1.91},"content_text":"新浪科技讯 12月28日下午消息，近日，人工智能领域国际会议AAAI 2026公布了论文录用结果，由小鹏汽车和北京大学计算机学院多媒体信息处理全国重点实验室联合完成的论文《FastDriveVLA： Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning》成功入选。这篇论文最大的贡献在于，提出了一种专门为端到端自动驾驶VLA模型定制的、高效的视觉Token剪枝框架——FastDriveVLA。\n　　据介绍，FastDriveVLA包含一个即插即用的视觉Token剪枝器ReconPruner。在车端模型的推理阶段， ReconPruner可直接嵌入自动驾驶VLA模型用于视觉Token的剪枝，即插即用，无需重新训练整个模型。为了辅助该剪枝器的训练，还专门构建了包含来自6个摄像头视角的24.1万个图像-掩码对的nuScenes-FG数据集。这一大规模的自动驾驶前景分割标注数据集，可广泛用于未来自动驾驶的研究。\n　　最终，nuScenes自动驾驶数据集上的测试显示，采用这一剪枝框架，在不同剪枝率下均取得当前最优即SOTA效果：剪枝比例达25%视觉Token时，驾驶性能几乎不下降，其L2轨迹误差与碰撞率指标甚至超越未剪枝的基准模型；剪枝比例达50%Token时，在所有指标上表现更平衡；与此同时，VLA模型的推理效率得到了显著提升。\n　　小鹏汽车联合北大提出的FastDriveVLA，建立了自动驾驶VLA模型的高效视觉Token剪枝的新范式，同时树立了车端大模型高效部署上车的新标杆。小鹏汽车董事长何小鹏在微博上对此表示，“很高兴我们在探索L4的路上又取得新的突破。我们会在物理AI领域继续发力，期待第二代VLA给鹏友们带来更棒的智驾体验。”\n\n\n\n海量资讯、精准解读，尽在新浪财经APP\n\n责任编辑：郭栩彤","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"1","news_tag":"","news_rank":0,"symbols":[],"gpt_button":0,"need_auth":false,"code":"91000000","status":"200"},"commentList":[],"isCommentEnd":true,"newsSizeData":{"likeSize":0,"commentSize":0,"repostSize":0,"favoriteSize":0,"likeStatus":false,"favoriteStatus":false},"APP":{"userAgent":"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)","isDev":false,"isTTM":false,"tenantId":"TBCN","deviceId":"web-server-community-laohu8-v3","version":"4.36.2","shortVersion":"4.36.2","platform":"web","vendor":"web","appName":"laohu8","isIOS":false,"isAndroid":false,"isTiger":false,"isTHS":false,"isWeiXin":false,"isWeiXinMini":false,"isWeiBo":false,"isQQ":false,"isBaiduSwan":false,"isBaiduBox":false,"isDingTalk":false,"isToutiao":false,"isOnePlus":false,"isHuaWei":false,"isXiaomi":false,"isXiaomiWebView":false,"isOppo":false,"isVivo":false,"isSamsung":false,"isMobile":false},"href":"/m/news/2594221852","isCrawlerRequest":true}