# Alibaba — Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

- Company: Alibaba (alibaba.com)
- Announced: 2026-09-03
- Category: new-model
- Coverage: 3 outlets
- Announcement: yes
- Group: models
- Source: https://qwen.ai/blog?id=qwen-drive-1.0
- Record: https://forck.live/items/7456-qwen-drive-1-0-an-initial-step-towards-a-vision-language-foundation-model-for
- Subject: Qwen
- Models affected: Qwen-Drive-1.0, Qwen3.5-4B

Alibaba introduces Qwen-Drive-1.0, a vision-language foundation model for autonomous driving built on Qwen3.5-4B. It unifies 3D perception, visual question answering, and motion planning by attaching a BEV perception head and a Planning Expert module. The model achieves competitive results on driving scene understanding and motion planning benchmarks.

## Evidence

Verbatim from https://qwen.ai/blog?id=qwen-drive-1.0:

> We introduce Qwen-Drive-1.0, the first vision-language foundation model for autonomous driving that unifies 3D perception and visual question answering at the pretraining stage and further extends to motion planning, while keeping the pretrained VLM architecture entirely untouched.

## Around this story

Outlets this record can name and link:

- Business Insider — Oura takes step toward IPO with S-1 filing, revealing $1.4 billion in revenue: https://businessinsider.com/oura-ring-s1-filing-step-towards-ipo-reveals-revenue-2026-9
- Morningstar: https://morningstar.com/news/marketwatch/20260903430/oura-files-for-ipo-amid-americans-obsession-with-tracking-their-sleep-steps-and-heart-rates
- Inc: https://inc.com/chris-morris/oura-is-going-public-and-theres-1-surprising-revenue-stream-driving-its-mega-ipo/91401708

---

Record: https://forck.live/items/7456-qwen-drive-1-0-an-initial-step-towards-a-vision-language-foundation-model-for
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md