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

arXiv 25.10 2025 71.6 method, system

TLDR

MorphoSim generates interactive, controllable 4D scenes from language, enabling object editing and multi-view consistency without full regeneration.

Reasoning

The paper introduces a novel framework for language-guided 4D scene generation with interactivity and editability, which is a strength. However, it lacks real-world evaluation and comparison to baselines, and the experimental details are sparse.

Read-first score

Read-first score 71.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 49.

Recency 8%

86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=True; dataset=False; markers=code,github

Topical relevance 42%

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=evaluation,experiment

Field roles

FrontierReproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 84.

Keyword Scores

world simulator

world model

interactive world model

generative world model

video world model

world dynamics prediction

model-based reinforcement learning world model

Deep Analysis

Innovations

Language-guided 4D world simulator with multi-view consistency and object-level controls
Interactive editing without full re-generation via integration of trajectory-guided generation and feature field distillation
Controllable and editable spatiotemporal environments for robotics applications

Methodology

MorphoSim integrates trajectory-guided generation with feature field distillation to produce dynamic 4D scenes from natural language instructions. It enables object-level controls such as directing, recoloring, or removing objects, and allows observation from arbitrary viewpoints. The framework supports interactive edits without requiring full re-generation.

Key Results

Experiments demonstrate that MorphoSim maintains high scene fidelity while enabling controllability and editability.

Resources

Paper Code