High-quality articulated 3D assets are indispensable for embodied AI and physical simulation, yet 3D generation still focuses on static meshes, leaving a gap in "sim-ready" interactive objects. Most recent articulated object creation methods rely on multi-stage pipelines that accumulate errors across decoupled modules. Alternatively, unified MLLMs offer a single-stage path to joint static asset understanding and sim-ready asset generation. However dense voxel-based 3D tokenization yields long 3D token sequences and high memory overhead, limiting scalability to complex articulated objects. To address this, we propose SIMART, a unified MLLM framework that jointly performs part-level decomposition and kinematic prediction. By introducing a Sparse 3D VQ-VAE, SIMART reduces token counts by 70% vs. dense voxel tokens, enabling high-fidelity multi-part assemblies. SIMART achieves state-of-the-art performance on PartNet-Mobility and in-the-wild AIGC datasets, and enables physics-based robotic simulation.

翻译：高质量的可关节化3D资产是具身人工智能与物理仿真中不可或缺的要素，然而当前的3D生成技术仍以静态网格为主，导致"可仿真"交互式物体存在空白。现有大多数关节化物体创建方法依赖多阶段流水线，此类方法会在解耦模块间累积误差。与之相对，统一的多模态大语言模型（MLLM）提供了单步路径，可同时实现静态资产理解与可仿真资产生成。然而基于稠密体素的3D分词化方案会产生过长的3D词元序列与高昂的内存开销，制约了向复杂关节化物体的可扩展性。为此，我们提出SIMART——一种联合执行部件级分解与运动学预测的统一MLLM框架。通过引入稀疏3D VQ-VAE，SIMART相比稠密体素词元将词元数量降低70%，从而支持高保真多部件装配。在PartNet-Mobility及野生AIGC数据集上，SIMART取得了最优性能，并实现了基于物理的机器人仿真。