{"id":56794,"date":"2026-09-06T20:47:27","date_gmt":"2026-09-06T12:47:27","guid":{"rendered":"https:\/\/www.1ai.net\/?p=56794"},"modified":"2026-09-06T20:47:27","modified_gmt":"2026-09-06T12:47:27","slug":"%e9%98%bf%e9%87%8c%e5%8d%83%e9%97%ae%e5%bc%80%e6%ba%90-qwen-drive-1-0-4b%ef%bc%9a%e9%a6%96%e4%b8%aa%e9%9d%a2%e5%90%91%e8%87%aa%e5%8a%a8%e9%a9%be%e9%a9%b6%e7%9a%84%e8%a7%86%e8%a7%89%e8%af%ad%e8%a8%80","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/56794.html","title":{"rendered":"Ali thousands Ask Source Qwen-Drive-1.0-4B: First visual language base model for autopilot"},"content":{"rendered":"<p>September 6, Ari<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%8d%83%e9%97%ae\" title=\"[See articles with [thousands of questions] labels]\" target=\"_blank\" >Questions<\/a>this week<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a>Qwen-Drive-1.0-4B, an autopilot based on Qwen3.5-4B<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%a7%86%e8%a7%89%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [visual language modeling]]\" target=\"_blank\" >visual language model<\/a>.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-56795\" title=\"04b14cej00tky0t00g7d000v9000h2p\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2026\/09\/04b14acej00tky0tw00g7d000v900h2p.jpg\" alt=\"04b14cej00tky0t00g7d000v9000h2p\" width=\"1125\" height=\"614\" \/><\/p>\n<p>Officially, Qwen-Drive-1.0<strong>First visual language base model for autopilot<\/strong>AT THE PRE-TRAINING STAGE, 3D PERCEPTION AND VISUAL QUESTIONS AND ANSWERS WERE HARMONIZED AND FURTHER EXTENDED TO SPORTS PLANNING, WHILE THE ORIGINAL VLM STRUCTURE FOR PRE-TRAINING WAS FULLY MAINTAINED\u3002<\/p>\n<p>The model uses a phased training programme that combines driving supervision with universal visual language data and retains universal visual understanding and command compliance while acquiring specific driving capabilities. Qwen-Drive-1.0-4B also provides two planning specialists, SFT and RL, with official assessments covering 3D perception, driving scenario understanding, universal visual language skills, and open, pseudo-closure and closed circle movement planning\u3002<\/p>\n<p>Description, Qwen-Drive-1.0\u00a0<strong>Only open-source construction of planned samples<\/strong>THE TRAJECTORIES OF THE VARIOUS DATA SETS WERE HARMONIZED AND A COMPREHENSIVE ASSESSMENT WAS CONDUCTED FROM THE OPEN-RING PREDICTION TO CLOSED-RING DRIVING. THE SFT MODEL IS COMPETITIVE ON ALL BENCHMARKS. AFTER INTENSIVE LEARNING, THE MODEL IS ONLY AT THE EXPENSE OF SMALL OPEN-RING ERROR, IN EXCHANGE FOR A COMPREHENSIVE UPGRADING IN HUMAN PREFERENCES AND THE SAFETY OF CLOSED-RINGS\u3002<\/p>\n<p>1AI WITH RELEVANT LINKS:<\/p>\n<ul>\n<li>GitHub: https:\/\/github.com\/QwenLM\/Qwen-Drive-1.0<\/li>\n<li>Hugging Face: https:\/\/huggingface.co\/Qwen\/Qwen-Drive-1.0-4B<\/li>\n<li>ModelScope: https:\/\/modelsscope.cn\/models\/Qwen\/Qwen-Drive-1.0-4B<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>On September 6th, Ali thousands asked for Qwen-Drive-1.0-4B, an automatic driving visual language model based on Qwen3.5-4B. Officially, Qwen-Drive-1.0 is the first visual language base model for auto-driving, which harmonizes 3D perception and visual questions and answers at the pre-training stage and further extends to sports planning, while retaining the original VLM structure for pre-training completely. The model uses a phased training programme that combines driving supervision with universal visual language data and retains universal visual understanding and command compliance while acquiring specific driving capabilities. Qwen-Drive-1.0-4B provides both SFT and RL programmes<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[7880,219,4981],"collection":[],"class_list":["post-56794","post","type-post","status-publish","format-standard","hentry","category-news","tag-7880","tag-219","tag-4981"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/56794","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=56794"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/56794\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=56794"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=56794"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=56794"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=56794"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}