Any4D: Open-Prompt 4D Generation from Natural Language and Images

While video-generation-based embodied world models have gained increasing attention, their reliance on large-scale embodied interaction data remains a key bottleneck. The scarcity, difficulty of collection, and high dimensionality of embodied data fundamentally limit the alignment granularity between language and actions and exacerbate the challenge of long-horizon video generation–hindering generative models from achieving a $\mathit{\text{"GPT}}\mathit{\text{moment"}}$ in the embodied domain. There is a naive observation: $\mathit{\text{the}}\mathit{\text{diversity}}\mathit{\text{of}}\mathit{\text{embodied}}\mathit{\text{data}}\mathit{\text{far}}\mathit{\text{exceeds}}\mathit{\text{the}}\mathit{\text{relatively}}\mathit{\text{small}}\mathit{\text{space}}\mathit{\text{of}}\mathit{\text{possible}}\mathit{\text{primitive}}\mathit{\text{motions}}$. Based on this insight, we propose $\mathbf{\text{Primitive}}\mathbf{\text{Embodied}}\mathbf{\text{World}}\mathbf{\text{Models}}$ (PEWM), which restricts video generation to fixed shorter horizons, our approach $\mathit{\text{1)}}\mathit{\text{enables}}$ fine-grained alignment between linguistic concepts and visual representations of robotic actions, $\mathit{\text{2)}}\mathit{\text{reduces}}$ learning complexity, $\mathit{\text{3)}}\mathit{\text{improves}}$ data efficiency in embodied data collection, and $\mathit{\text{4)}}\mathit{\text{decreases}}$ inference latency. By equipping with a modular Vision-Language Model (VLM) planner and a Start-Goal heatmap Guidance mechanism (SGG), PEWM further enables flexible closed-loop control and supports compositional generalization of primitive-level policies over extended, complex tasks. Our framework leverages the spatiotemporal vision priors in video models and the semantic awareness of VLMs to bridge the gap between fine-grained physical interaction and high-level reasoning, paving the way toward scalable, interpretable, and general-purpose embodied intelligence.