LAM: Language Articulated Object Modelers

ICLR 2026 Conference Submission14228 Authors

Keywords: Articulated Objects; 3D Generation

Abstract: We introduce LAM, a system that explores the collaboration of large-language models and vision-language models to generate articulated objects from text prompts. Our approach differs from previous methods that either rely on input visual structure(e.g., an image) or assemble articulated models from pre-built assets. In contrast, we formulate articulated object generation as a unified code generation task, where 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. The LAM first reasons about the hierarchi-= cal structure of parts (links) with Link Designer, then writes code, compiles it, and debugs it with Geometry & Articulation Coders and self-corrects with Geometry & Articulation Checkers. The code serves as a structured and interpretable bridge between individual links, ensuring correct relationships among them. Representing everything with code allows the system to determine appropriate joint types and calculate their exact placements more reliably. Experiments demonstrate the power of leveraging code as a generative medium within an agentic system, showcasing its effectiveness in automatically constructing complex articulated objects.

Primary Area: generative models

Submission Number: 14228