arXiv:2608.31025v1 Announce Type: new Abstract: Inferring object dynamics from visual observations is essential for intelligent agents to reason about and interact with the physical world, yet remain...
arXiv:2603. 03485v3 Announce Type: replace-cross Abstract: Recent video diffusion models have achieved impressive capabilities as large-scale generative world models.
arXiv:2605. 00412v3 Announce Type: replace Abstract: World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning.
Neural Voxel Dynamics introduces a self‑supervised framework that learns 3D latent dynamics from monocular video by unprojecting V‑JEPAs features into a voxel grid using depth priors. It then applies Volumetric Feature Advection, an action‑conditioned transition model, to predict the evolution of these latent features directly in 3D, without relying on privileged physics‑engine states. The method is evaluated on synthetic and real datasets, demonstrating predictive fidelity, 3D geometric consistency, and physical plausibility via Physics‑IQ metrics.
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.
Synthesizing realistic Human-Object Interactions (HOI) is critical for creating embodied avatars and functional virtual environments. However, current data-driven approaches primarily rely on motion capture datasets, which are expensive to scale and limited in functional diversity.
Dream4D is a new framework for generating spatiotemporally coherent 4D content. It uses a two‑stage pipeline: first, few‑shot learning predicts optimal camera trajectories from a single image; second, a pose‑conditioned diffusion process creates geometrically consistent multi‑view sequences that are converted into a persistent 4D representation. The method uniquely combines rich temporal priors from video diffusion models with geometric awareness from reconstruction models, achieving higher quality metrics such as mPSNR and mSSIM compared to existing approaches.
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.
We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel space, leaving the underlying world dynamics implicit within high-dimensional visual predictors.
arXiv:2609.18430v1 Announce Type: new Abstract: Modeling physical dynamics, including how objects move, interact, and change state, is central to video world models for embodied AI. We present StrucP...
The paper introduces GenSight, a unified embodied world model that combines future video generation and dense perception into a single pretrained video diffusion transformer. GenSight employs a shared spatiotemporal representation for video, depth, embodiment segmentation, and first‑frame‑relative 2D flow, and uses lightweight task modulation to predict all modalities within the same architecture. The model supports both multi‑step future video generation with aligned dense predictions and single‑step dense perception from an observed video, demonstrating strong performance on embodied manipulation data across multiple robot embodiments and human‑hand interactions.
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...