The paper introduces 4DGS-WAM, an object‑centric world action model that uses a 4D Gaussian Splatting representation to separate dynamic objects from a static background. By predicting future actions of dynamic actors and their Gaussian splat transformations, the model can reuse previously observed static content for future state generation, reducing redundant background processing. Experiments on the KITTI‑MOT dataset demonstrate the model’s ability to perform short‑horizon prediction and past reconstruction.
arXiv:2610.28631v1 Announce Type: new Abstract: Current world models for explicit world simulation typically follow two distinct pathways: (1) video generative models (e.g., Sora), which simulate rea...
arXiv:2606. 01950v1 Announce Type: cross Abstract: World models enable intelligent agents to predict the consequences of their actions on the environment.
arXiv:2610.24812v2 Announce Type: replace Abstract: 3D Gaussian Splatting has made high-fidelity 3D reconstruction fast and accessible, yet existing representations assume a static world. This assump...
arXiv:2606.18250v2 Announce Type: replace Abstract: Forecasting the evolution of dynamic environments is crucial for autonomous agents. While generative world models have achieved high photorealism i...
StateCraft introduces a new architecture that separates a persistent, updatable abstract state from the visual state in video world models. By pairing a language model with a video diffusion model, it tracks entity changes over time and conditions visual generation on this abstract state. The approach is evaluated on generative interfaces and a new benchmark, showing improved generation quality, memory usage, and controllability, while enabling direct editing of unseen states and extending to spatial 3D environments.
arXiv:2601.15951v2 Announce Type: replace Abstract: Novel view synthesis (NVS) of static and dynamic urban scenes is essential for autonomous driving simulation, yet existing methods often struggle t...
arXiv:2604. 09877v2 Announce Type: replace-cross Abstract: At the intersection of computer vision and robotic perception, 4D reconstruction of dynamic scenes connects low-level geometric sensing with high-level semantic understanding.
Box-WAM introduces a new approach to world action models (WAMs) by replacing dense future video predictions with oriented bounding box trajectories of task-relevant objects. This compact, object-centric representation reduces computational cost during training and inference while improving action prediction performance. The method demonstrates that box trajectory prediction can serve as an efficient alternative to full-frame video-based world action modeling for robotic manipulation tasks.
arXiv:2610.17526v1 Announce Type: cross Abstract: World action models (WAMs) are a category of policy models that ex- plicitly predict both actions and future world states. They have been shown to ou...
arXiv:2610.35854v1 Announce Type: new Abstract: 4D novel view synthesis (NVS) aims to render dynamic scenes across viewpoints and timestamps, which requires jointly inferring 3D structure and tempora...
arXiv:2609.00994v1 Announce Type: new Abstract: Recent extensions of 3D Gaussian Splatting (3DGS) enable real-time novel view synthesis in dynamic scenes by learning time-conditioned Gaussian deforma...
arXiv:2610.28594v1 Announce Type: new Abstract: Reliable multi-view forecasting requires videos from different cameras to describe the same evolving 3D scene. To this end, we introduce Video-Point Mo...