Score: 1

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model

Published: November 17, 2025 | arXiv ID: 2511.13647v1

By: Chunshi Wang , Junliang Ye , Yunhan Yang and more

Potential Business Impact:

Lets computers build and change 3D objects with words.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RGB point cloud and a natural language prompt, our model autoregressively generates a single, coherent token sequence encoding part-level bounding boxes, semantic descriptions, and edit commands. This structured output serves as a versatile interface to drive downstream geometry-aware modules for part-based generation and editing. By decoupling the symbolic planning from the geometric synthesis, our approach allows any compatible geometry engine to be controlled through a single, language-native frontend. We pre-train a dual-encoder architecture to disentangle structure from semantics and instruction-tune the model on a large-scale, part-centric dataset. Experiments demonstrate that our model excels at producing high-quality, structured plans, enabling state-of-the-art performance in grounded Q\&A, compositional generation, and localized editing through one unified interface. Project page: https://chunshi.wang/Part-X-MLLM/

Page Count
28 pages

Category
Computer Science:
CV and Pattern Recognition