홈 › Papers

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

2025-08-02 · Shuangkang Fang, I-Chao Shen, Yufeng Wang, Yi-Hsuan Tsai, Yi Yang, Shuchang Zhou, Wenrui Ding, Takeo Igarashi, Ming-Hsuan Yang arxiv

We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in existing methods, including the limited dataset scale when catering to LLMs' token length and the loss of 3D structural information during mesh serialization. We introduce a Primitive-Mesh decomposition strategy, which divides 3D meshes into structurally meaningful subunits. This enables the creation of a large-scale dataset with 1500k+ samples, almost 50 times larger than previous methods, which aligns better with the LLM scaling law principles. Furthermore, we propose inferring face connectivity from vertices and local mesh assembly training strategies, significantly enhancing the LLMs' ability to capture mesh topology and spatial structures. Experiments show that MeshLLM outperforms the state-of-the-art LLaMA-Mesh in both mesh generation quality and shape understanding, highlighting its great potential in processing text-serialized 3D meshes.

📄 PDF Abstract BibTeX arXiv:2508.01242

Code (0)

등록된 구현이 없습니다.

TalkUp: Paving the Way for Understanding Empowering Language

2023-05-23 · Lucille Njoo, Chan Young Park, Octavia Stappart, Marvin Thielk 외

Empowering language is important in many real-world contexts, from education to workplace dynamics to healthcare. Though language technologies are growing more prevalent in these contexts, empowerment has seldom been stu…

Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum Learning

2024-05-28 · Dongjie Chen, Kartik Patwari, Zhengfeng Lai, Sen-ching Cheung 외

Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to a target domain using only unlabeled target data. Current SFDA methods face challenges in effectively leveraging pre-trained knowledge and …

Domain Adaptation Instruction Following Source-Free Domain Adaptation Transfer Learning+1

WorldGPT: Empowering LLM as Multimodal World Model

2024-04-28 · Zhiqi Ge, Hongzhe Huang, Mingze Zhou, Juncheng Li 외

World models are progressively being employed across diverse fields, extending from basic environment simulation to complex scenario construction. However, existing models are mainly trained on domain-specific states and…

Language Modeling Language Modelling Large Language Model model+1

OCC-MLLM:Empowering Multimodal Large Language Model For the Understanding of Occluded Objects

2024-10-02 · Wenmo Qiu, Xinhan Di

There is a gap in the understanding of occluded objects in existing large-scale visual language multi-modal models. Current state-of-the-art multimodal models fail to provide satisfactory results in describing occluded o…

Language Modeling Language Modelling Large Language Model Multimodal Large Language Model

Empowering Large Language Models for Textual Data Augmentation

2024-04-26 · Yichuan Li, Kaize Ding, Jianling Wang, Kyumin Lee

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented dat…

Data Augmentation Diversity Few-Shot Learning