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

EPISODE · Nov 19, 2025 · 25 MIN

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

from Daily Paper Cast · host Jingwen Liang, Gengyu Wang

🤗 Upvotes: 63 | cs.CV Authors: Chunshi Wang, Junliang Ye, Yunhan Yang, Yang Li, Zizhuo Lin, Jun Zhu, Zhuo Chen, Yawei Luo, Chunchao Guo Title: Part-X-MLLM: Part-aware 3D Multimodal Large Language Model Arxiv: http://arxiv.org/abs/2511.13647v1 Abstract: 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/

Episode metadata supplied by the publisher feed · Published Nov 19, 2025

🤗 Upvotes: 63 | cs.CV Authors: Chunshi Wang, Junliang Ye, Yunhan Yang, Yang Li, Zizhuo Lin, Jun Zhu, Zhuo Chen, Yawei Luo, Chunchao Guo Title: Part-X-MLLM: Part-aware 3D Multimodal Large Language Model Arxiv: http://arxiv.org/abs/2511.13647v1 Abstract: 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/

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

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

0:00 25:57

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Daily Paper Cast?

This episode is 25 minutes long.

When was this Daily Paper Cast episode published?

This episode was published on November 19, 2025.

What is this episode about?

🤗 Upvotes: 63 | cs.CV Authors: Chunshi Wang, Junliang Ye, Yunhan Yang, Yang Li, Zizhuo Lin, Jun Zhu, Zhuo Chen, Yawei Luo, Chunchao Guo Title: Part-X-MLLM: Part-aware 3D Multimodal...

Can I download this Daily Paper Cast episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!