RESEARCH PAPER

Programmable World Model

Zheng-Hui Huang; Guixu Lin; Jiacheng Lin; Yi-Chuan Huang; Ruihan Yu; Muyao Niu; Siqi Yang; Yu-Lun Liu; Yung-Yu Chuang; Kaipeng Zhang; Zhixiang Wang

Classification

View four quadrants
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Not assigned

Category review. An explicit rule engine updates user-action-conditioned world state and a neural renderer produces observations; this is a programmable interactive neural simulator, without its own learned action policy. The cataloged contribution is a dataset/data-generation method or evaluation/simulation resource, not the architecture of an evaluated or external policy. Reading evidence

AT A GLANCE

Contribution

Programmable World Model makes a rule-executing engine authoritative for world facts and uses a conditioned video model to render them. State-augmented 3D oriented bounding boxes connect these components without requiring detailed animated assets. On CombatStateBench, the system reports 94% visible-alive-count accuracy and 98% death-state accuracy, but these permissive global metrics do not establish correct entity-specific interactions or autonomous action selection (e-world, e-controls, e-table, e-metrics).

Abstract

An abstract has not been added yet.

Affiliations

Alaya Lab