MorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator

World models that support controllableand editable spatiotemporal environments are valuablefor robotics, enabling scalable training data, repro ducible evaluation, and flexible task design. Whilerecent text-to-video models generate realistic dynam ics, they are constrained to 2D views and offer limitedinteraction. We introduce MorphoSim, a language guided framework that generates 4D scenes withmulti-view consistency and object-level controls. Fromnatural language instructions, MorphoSim producesdynamic environments where objects can be directed,recolored, or removed, and scenes can be observedfrom arbitrary viewpoints. The framework integratestrajectory-guided generation with feature field dis tillation, allowing edits to be applied interactivelywithout full re-generation. Experiments show that Mor phoSim maintains high scene fidelity while enablingcontrollability and editability. The code is availableatthis https URL.