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:2606. 01950v1 Announce Type: cross Abstract: World models enable intelligent agents to predict the consequences of their actions on the environment.
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...
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.
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:2607. 01202v1 Announce Type: cross Abstract: We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos.
arXiv:2603. 03482v2 Announce Type: replace-cross Abstract: Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities.
arXiv:2603. 03485v3 Announce Type: replace-cross Abstract: Recent video diffusion models have achieved impressive capabilities as large-scale generative world models.
Forge4D is a feed‑forward model that reconstructs temporally aligned 4D human representations from uncalibrated sparse‑view videos, enabling both novel view and novel time synthesis. It achieves this by jointly streaming 3D Gaussian reconstruction with dense motion prediction, using learnable state tokens for temporal consistency and a self‑supervised retargeting loss for motion prediction. Extensive experiments confirm its effectiveness on in‑domain and out‑of‑domain datasets.
GeoWAM introduces a visual geometry world action model that predicts future scene geometry instead of future images, using point clouds to capture spatial structure and transformations. The model is pretrained to forecast geometry, then a geometry-conditioned action head predicts ego trajectories. Experiments show that this geometry-based approach yields stronger driving policies than image-based alternatives.
The paper introduces Spatially Aware World Action Model (SA‑WAM), a diffusion‑based framework that extends existing World Action Models by incorporating depth information alongside RGB to enable 3‑D‑aware action and future‑state prediction. SA‑WAM repurposes a pretrained video diffusion model, using a nonlinear encoding to map unbounded depth into the tokenizer’s bounded domain, thus preserving pretrained visual priors without 3‑D‑specific fine‑tuning. The model achieves state‑of‑the‑art performance on RoboCasa and LIBERO‑Plus benchmarks and demonstrates superior real‑world performance on a UR5 robotic arm in randomized environments, while also providing analysis linking world‑model prediction quality to rollout success.
arXiv:2606. 17046v1 Announce Type: cross Abstract: Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world.
arXiv:2608. 11605v1 Announce Type: new Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction.