LAM：语言驱动的铰接物体建模器
LAM: Language Articulated Object Modelers
把铰接物体的几何与关节结构统一表示为可编译、可自纠错的过程化代码，为视觉研究者提供了一条无需视觉先验或预置 3D 资产、由 LLM/VLM 协作直接产出带关节层级 3D 模型的路径，可作为 3D 生成与具身仿真中资产构建的新范式。
原文依据 formulate articulated object generation as a unified code-generation task, in which geometry and articulations can be co-designed from scratch
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 LAM，一个探索大语言模型与视觉语言模型协作的系统，可在没有视觉先验或预置 3D 资产的情况下，根据文本提示生成铰接物体。与之相对，我们将铰接物体生成形式化为一个统一的代码生成任务，使几何与关节结构能够从零开始协同设计。给定输入文本，LAM 协调一组专用模块，生成以过程化方式表示目标铰接物体的代码。LAM 首先由 Link Designer 推理部件（连杆）的层级结构，随后由 Geometry and Articulation Coders 编写代码、编译并调试，并由 Geometry and Articulation Checkers 进行自我纠正。代码作为各连杆之间结构化、可解释的桥梁，确保它们之间的正确关系。实验证明了在协作系统中将代码作为生成媒介的能力，展示了其在自动构建复杂铰接物体方面的有效性。
英文原文摘要 1061 字符
We introduce LAM, a system that explores collaboration between large language models and vision-language models to generate articulated objects from text prompts without a visual prior or prebuilt 3D assets. In contrast, we formulate articulated object generation as a unified code-generation task, in which geometry and articulations can be co-designed from scratch. Given an input text, LAM coordinates a team of specialized modules to generate code to represent the desired articulated object procedurally. LAM first reasons about the hierarchical structure of parts (links) with Link Designer, then writes code, compiles it, and debugs it with Geometry and Articulation Coders and self-corrects with Geometry and Articulation Checkers. The code serves as a structured, interpretable bridge between individual links, ensuring the correct relationships among them. Experiments demonstrate the power of leveraging code as a generative medium within a collaboration system, showcasing its effectiveness in automatically constructing complex articulated objects.