AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving

Yingyan Li, Shuyao Shang, Weisong Liu, Bing Zhan, Haochen Wang, Yuqi Wang, Yuntao Chen, Xiaoman Wang, AnYasong, Chufeng Tang, Lu Hou, Lue Fan and 1 more

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 113 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add action grounding (interleaved vision-action 6VA) to vision-only world-model pretraining (ablation)VLA-W0-VQ · NAVSIMPDMS: 84.1 -> 85.6Improved
lengthen pretraining sequence from VA to 6VA (ablation)VLA-W0-VQ · NAVSIMPDMS: 83.3 -> 85.6Improved
lengthen pretraining sequence from 2VA to 6VA (ablation)VLA-W0-VQ · NAVSIMPDMS: 84.2 -> 85.6Improved
add NuPlan world-model pretraining before NAVSIM finetuning (ablation)VLA-W0-VQ · NAVSIMPDMS: 80.7 -> 85.6Improved
add NuPlan pretraining to action-only VLA baselineVLA-VQ · NAVSIMPDMS: 68.7 -> 62.2Hurt
add NuPlan pretraining to TransFuser-7BTransFuser-7B · NAVSIMPDMS: 77.9 -> 71.6Hurt
add world modeling to VQ VLA at 70M framesVLA (VQ) · In-house dataset (70M frames)ADE (m): 1.4829 -> 1.0563Improved
add world modeling to ViT VLA at 70M framesVLA (ViT) · In-house dataset (70M frames)Collision (%): 0.0359 -> 0.0302Improved
add world modeling to ViT VLA at 700k framesVLA (ViT) · In-house dataset (700k frames)Collision (%): 0.0462 -> 0.0513Hurt
add world modeling to VQ VLA at 700k framesVLA (VQ) · In-house dataset (700k frames)ADE (m): 1.5424 -> 1.5985Hurt
swap query-based action expert for autoregressive expert at 70M framesVLA · In-house dataset (70M frames)Collision (%): 0.0453 -> 0.0295Improved
swap query-based action expert for autoregressive expert on NAVSIMVLA · NAVSIM (103k frames)PDMS: 88.4 -> 85.3Hurt

Later papers that compared with this method

8 later accepted papers report DriveVLA-W0 as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy