DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917540473602048 |
|---|---|
| author | Shi, Chen Xu, Jinrui Shi, Shaoshuai Sheng, Kehua Zhang, Bo Jiang, Li |
| author_facet | Shi, Chen Xu, Jinrui Shi, Shaoshuai Sheng, Kehua Zhang, Bo Jiang, Li |
| contents | Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture temporal dynamics and motion priors that are naturally suited for driving. We present DriveWAM, a driving world-action model that adapts a pretrained video diffusion transformer into an autoregressive video-action policy. DriveWAM organizes video and action streams into a unified temporal token sequence and trains them under a joint flow-matching objective, preserving the pretrained video-generation architecture while adapting its large-scale video priors to action generation. To incorporate high-level scene understanding, we introduce scene-evolving driving guidance, where a frozen VLM produces chunk-specific semantic intent to guide video-action generation. To keep long-horizon rollout bounded, we further introduce selective KV memory, which maintains bounded modality-aware video and action memory pools through relevance-redundancy cache selection at inference time. Experiments on NAVSIM and the PhysicalAI-Autonomous-Vehicles benchmark show that DriveWAM achieves strong planning performance, and a data-scaling study from 4k to 100k driving clips further confirms the scaling potential of world-action modeling for end-to-end autonomous driving. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28544 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving Shi, Chen Xu, Jinrui Shi, Shaoshuai Sheng, Kehua Zhang, Bo Jiang, Li Computer Vision and Pattern Recognition Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture temporal dynamics and motion priors that are naturally suited for driving. We present DriveWAM, a driving world-action model that adapts a pretrained video diffusion transformer into an autoregressive video-action policy. DriveWAM organizes video and action streams into a unified temporal token sequence and trains them under a joint flow-matching objective, preserving the pretrained video-generation architecture while adapting its large-scale video priors to action generation. To incorporate high-level scene understanding, we introduce scene-evolving driving guidance, where a frozen VLM produces chunk-specific semantic intent to guide video-action generation. To keep long-horizon rollout bounded, we further introduce selective KV memory, which maintains bounded modality-aware video and action memory pools through relevance-redundancy cache selection at inference time. Experiments on NAVSIM and the PhysicalAI-Autonomous-Vehicles benchmark show that DriveWAM achieves strong planning performance, and a data-scaling study from 4k to 100k driving clips further confirms the scaling potential of world-action modeling for end-to-end autonomous driving. |
| title | DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.28544 |