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.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
SpatialCrafter introduces a two‑stage framework for single‑image world modeling that first generates a global 3D proxy using a Point‑anchored Sparse Structure Flow module, then refines appearance with a Generative Deferred Refiner built on a video diffusion model. The method incorporates Parallel Geometry Injection and Proxy‑Aware Corruption training to integrate the proxy without disrupting the pretrained generative manifold, and it is evaluated on a newly constructed dataset of 115K scenes. Experiments demonstrate that SpatialCrafter outperforms existing approaches, reducing long‑term drift and maintaining consistency under rapid camera motion and extreme viewpoints.
arXiv:2608.29910v1 Announce Type: new Abstract: Interactive world models extend video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling appli...
arXiv:2609.10540v1 Announce Type: new Abstract: Recent video world models generate increasingly realistic and interactive visual experiences, yet lack reliable mechanisms for maintaining persistent w...
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...
The paper introduces the Geometry‑Native Autoencoder (GAE), a compact latent space that can be decoded into appearance, depth, camera parameters, and point maps, enabling 3D‑consistent world generation. By reparameterizing a geometry foundation model’s features, GAE replaces traditional appearance‑centric latents and improves visual quality and 3D coherence, achieving significant reductions in FVD and camera‑trajectory error on benchmark datasets. The work demonstrates that a geometry‑native latent space can serve as a shared interface between perception and generation models.
Puffin-World is a unified multimodal architecture that integrates physical understanding, spatial simulation, and 3D world generation without external offline modules. It jointly models physics, geometry, and appearance as native world states and uses a unified Omni-Camera representation to support diverse tasks and flexible motions. The framework also propagates physical dynamics across future frames, couples appearance and geometry in a single generative process, and scales to complex scenarios with the Puffin-16M dataset of 15 million vision‑language‑camera triplets and 1 million trajectories.