RESEARCH PAPERYear 2026

Ctrl-World: A Controllable Generative World Model for Robot Manipulation

Yanjiang Guo; Lucy Xiaoyang Shi; Jianyu Chen; Chelsea Finn

Classification

View four quadrants
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. Ctrl-World adapts SVD into an action-conditioned, joint-camera robot simulator. A separate policy and action-to-pose adapter supply controls, and humans evaluate or select simulated trajectories. The contribution is the simulator interface and rollout model, not a general video backbone. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX