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

TL;DR

This paper introduces PEWM, a framework that enhances embodied world models by focusing on primitive, short-horizon video generation, enabling better language-action alignment, data efficiency, and flexible control.

Contribution

PEWM restricts video generation to short horizons, improving alignment, efficiency, and inference speed, and incorporates a modular VLM planner with a Start-Goal heatmap for complex task generalization.

Findings

Enables fine-grained language and action alignment.

Reduces learning complexity and data requirements.

Supports flexible, compositional control of primitive policies.

Abstract

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 \textit{"GPT moment"} in the embodied domain. There is a naive observation: \textit{the diversity of embodied data far exceeds the relatively small space of possible primitive motions}. Based on this insight, we propose \textbf{Primitive Embodied World Models} (PEWM), which restricts video generation to fixed shorter horizons, our approach \textit{1) enables} fine-grained alignment between linguistic concepts and visual representations of robotic actions, \textit{2) reduces} learning complexity, \textit{3) improves} data efficiency in embodied data collection, and \textit{4) 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.