Skip to content
Preprint

4D-WAM: 4D Consistent World Modeling for Autonomous Driving

Aug 2026 · 1 citation · ⚡ 1 influential · 19 references
Computer Science

TL;DR

4D-WAM is presented, a model that leverages geometric foundation models for training-time supervision to enable 4D consistent world modeling and effectively models 4D consistent scene evolution and achieves state-of-the-art performance on challenging NAVSIM-v1 and NAVSIM-v2 benchmarks.

Abstract

Emerging World-Action Models (WAMs) have demonstrated promising performance in autonomous driving by jointly modeling future driving scene evolution and trajectory planning. However, existing WAMs are typically trained with video data, which is only 2D projections of the underlying 4D driving scene. Consequently, WAMs fail to understand and capture the structure of 4D scenes and thus generate visually plausible yet 4D inconsistent future predictions that mislead downstream planning. To alleviate this issue, we present 4D-WAM, a model that leverages geometric foundation models for training-time supervision to enable 4D consistent world modeling. Specifically, we feed WAM-predicted future frames into a geometric foundation model, and use 4D-aware responses to define a 4D consistency loss. This loss encourages the model to understand, represent, and predict physically consistent 4D scenes during training, without additional inference cost. Moreover, we identify an early-decision phenomenon in WAMs and propose a decision-oriented timestep sampling strategy that emphasizes supervision at early, high-noise stages, where driving decisions are primarily formed. By propagating 4D supervision to this critical decision-formation phase, the proposed strategy further improves trajectory planning. Extensive experiments demonstrate that 4D-WAM effectively models 4D consistent scene evolution and achieves state-of-the-art performance on challenging NAVSIM-v1 and NAVSIM-v2 benchmarks.

View source

Similar papers

Preprint Sep 2026

SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving

SV-WAM is proposed, a surround-view world-action model (WAM) that preserves full six-camera observations while maintaining efficient inference and introduces a differentiable drivable-area compliance regularizer that penalizes vehicle-footprint corners approaching or crossing drivable boundaries, improving planning saf...

Jin-Yang Wang, Shi-Wei Li, Jun-Jian Wang et al. · 1 citation
Sep 2026

V2X-WAM: A Cooperative World Action Model for End-to-End Autonomous Driving

Experiments on a large-scale real-world cooperative driving dataset demonstrate that V2X-WAM consistently improves planning accuracy and safety over representative end-to-end cooperative driving methods, while achieving stronger future-world prediction and substantially lower communication overhead.

Jun-Wei You, Wei-Zhe Tang, Can Wang et al. · 1 citation
#artificial intelligence Preprint Aug 2026

DA-WAM: Decision-Aligned Future Latents for Driving World Models

DA-WAM is proposed, a framework that unifies predictive representation learning, action-conditioned future modeling, and trajectory scoring under a single decision-making objective and demonstrates state-of-the-art performance on NAVSIM-v1 and NAVSIM-v2.

Rui-Guo Zhong, Ben-Shan Ma, Xiao-Long Chen et al. · 5 citations
Preprint Oct 2026

VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving

VGGT provides a strong foundation for geometry-centric world models by recovering unified 3D scene geometry from visual observations. Although recent extensions enable temporal 3D prediction, their future evolution remains weakly conditioned on driving intentions and actions, limiting their ability to model alternative...

Zhao-Yang Liu, Kun Jiang, Zi-Ying Song et al. · 0 citations
Preprint Oct 2026

SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models

Driving world action models (WAMs) learn from paired trajectories and future observations. Post-training with reinforcement learning allows the policy to explore alternative trajectories and improve planning using driving rewards. However, driving logs contain future videos only for the recorded trajectories, leaving t...

Chang-Hui Jing, Hao-Chen Tian, Hong-Chen Li et al. · 1 citation
Preprint Sep 2026

PhysWAM: Physically Consistent World Action Model for Autonomous Driving

PhysWAM is presented, a unified world-action model for autonomous driving that co-denoises multiview video, metric depth, and ego motion within a single flow-matching transformer and Coupled Point Projection is introduced, demonstrating that the geometric relationship between scene depth and ego motion provides a direc...

Dhruv Parikh, Feng-Cheng Yu, Quan-Kai Gao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.