SOURCE-LINKED INTELLIGENCE

StrucPhysVideo: Learning Physical Dynamics from Structured Captions and Robot Actions

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Modeling physical dynamics, including how objects move, interact, and change state, is central to video world models for embodied AI. We present StrucPhysVideo, a family of video world models that bridges physics-focused data curation with language- and action-conditioned prediction of scene evolution. Our data pipeline combines motion-aware video segmentation, quality and content filtering, and physical relevance verification with structured annotations of objects, materials, and temporally localized interactions. By disentangling camera motion from object behavior and explicitly describing c

Read original source ↗ Open in workspace

recordType

paper

region

Global