Robot-Native World Action Model Debuts With Spatiotemporal Architecture From Fudan-Linked Team

机器人原生世界动作模型问世！首创时空一体架构，复旦系团队出品

Moushen Intelligence released STI-WM, a spatiotemporally integrated world action model for robotics, with RGB, depth point cloud, and proprioceptive inputs; the post says it supports hundred-second-scale long-horizon task rollout and closed-loop replanning, but does not disclose benchmark scores or deployment costs.

Why it matters: HKR-H/K/R all pass: the STI-WM angle is novel, with concrete input modalities and hundred-second rollouts. Kept near the featured floor because public weights, benchmark results, and reproducible tests are not disclosed.