model · first seen 19 Oct 2026
driving world model
Also: generative driving video, world models for autonomous driving
A generative model that predicts future autonomous driving sensor observations given control signals.
Driving world models are generative models that predict future driving sensor data (camera video, depth, LiDAR, BEV layouts) conditioned on ego actions or plans, used as simulators and planning aids for end-to-end autonomous driving. The recent arXiv papers move past plain video generation. They cover feedforward 4D Gaussian reconstruction from generated multimodal video, unified tokenizers for world-action models, and joint perspective and BEV generation for reactive agents. Others propose panoramic multi-camera generation, rollout-free trajectory scoring, and safety post-training. Two papers critique the field: one on survivorship bias toward benign futures, one showing that released models move the camera but not the scene. The authors are spread across many academic and industry groups.
If these models become reliable enough to reflect the real consequences of a plan, they could replace part of costly real-world testing and give closed-loop training signals for driving policies. The papers on survivorship bias and on control evaluation suggest that measuring that reliability is now a research problem in its own right.
Analyst note (emerging), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 8 on 16 Nov 2026 · 7 mentions in 28 days · 7 independent groups · papers · first seen 4 weeks ago · acceleration +1.25
Earliest sources
- Drive2Gauss: FeedForward 4D Gaussian Reconstruction from Multimodal Generative Driving VideosPapers · 19 Oct 2026 · Tong Zhao, Zhiyuan Han, Lin Chen, Bowen Xie, Yunxi Qiao, Bohan Li, Weiqing Xiao,…
- DriveUniTok: A Unified Multimodal Tokenizer for Driving World-Action ModelsPapers · 26 Oct 2026 · Jingbo Xu, Hanchao Leng, JiaHui Huang, Hanbing Li, Jingwei Zhao, Kuiyuan Yang, C…
- Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous DrivingPapers · 3 Nov 2026 · Junzhe Wang, Jinqing Zhang, Qingjie Liu
- Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action ModelPapers · 5 Nov 2026 · Zihao Zhang, Xinyu Zhang, Bing Zeng, Xingyu Chen, Zhenning Li, Bin Yu, Ziyuan Pu
- Breaking survivorship bias in driving world modelsPapers · 8 Nov 2026 · Zihao Sheng, Zilin Huang, Yuhao Luo, Zhengyang Wan, Boyue Wang, Soyoung Ahn, Dav…
- BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World ModelPapers · 10 Nov 2026 · Junyoung Seo, Jaewoo Seo, Seungryong Kim, Laura Leal-Taixé, Xiuming Zhang, Seun…
Latest sources
- PanDWM: Panoramic 4D Driving World ModelsPapers · 15 Nov 2026 · Jiajun Sun, Zeyu Zhang, Zeyu Ren, Guangfeng Jiang, Yang Zhao, Hao Tang
- Driving World Models Move the Camera, Not the ScenePapers · 11 Nov 2026 · Yuqiao Feng, Xiaoyu Ao
- BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World ModelPapers · 10 Nov 2026 · Junyoung Seo, Jaewoo Seo, Seungryong Kim, Laura Leal-Taixé, Xiuming Zhang, Seun…
- Breaking survivorship bias in driving world modelsPapers · 8 Nov 2026 · Zihao Sheng, Zilin Huang, Yuhao Luo, Zhengyang Wan, Boyue Wang, Soyoung Ahn, Dav…
- Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action ModelPapers · 5 Nov 2026 · Zihao Zhang, Xinyu Zhang, Bing Zeng, Xingyu Chen, Zhenning Li, Bin Yu, Ziyuan Pu
- Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous DrivingPapers · 3 Nov 2026 · Junzhe Wang, Jinqing Zhang, Qingjie Liu
- DriveUniTok: A Unified Multimodal Tokenizer for Driving World-Action ModelsPapers · 26 Oct 2026 · Jingbo Xu, Hanchao Leng, JiaHui Huang, Hanbing Li, Jingwei Zhao, Kuiyuan Yang, C…
- Drive2Gauss: FeedForward 4D Gaussian Reconstruction from Multimodal Generative Driving VideosPapers · 19 Oct 2026 · Tong Zhao, Zhiyuan Han, Lin Chen, Bowen Xie, Yunxi Qiao, Bohan Li, Weiqing Xiao,…