CAPruner

This repository contains the official checkpoints and inference results for the PyTorch implementation of the paper:

Shengli Zhou, Xiangchen Wang, Guanhua Chen, and Feng Zheng. 2026. CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics.

Overview

Large language models (LLMs) have recently been applied to 3D vision-language (3D-VL) tasks, in which spatial reasoning is required to identify target objects based on their positions relative to others (i.e., anchors). To facilitate effective scene layout understanding, scene graphs are commonly used to represent such spatial relations. However, reasoning over full graphs incurs high token costs and computational inefficiencies, motivating the use of scene graph pruning.

Conceptual-Adjacent Scene Graph Pruner (CAPruner) integrates fuzzy semantic relevance with spatial proximity to estimate relation importance, enabling the selection of critical relations in a task-specific context. Moreover, to avoid costly relation-level annotations, CAPruner is trained by supervising the aggregated scores of each node's incident edges. Extensive experiments demonstrate that CAPruner effectively preserves relations essential for spatial reasoning, leading to substantial performance improvements of LLMs on 3D-VL tasks.

Usage

Please refer to the official GitHub repository for environment installation, data preparation, training, and inference instructions.

Acknowledgement

We would like to thank the anonymous reviewers for their constructive feedback.

Citation

If you find this project useful in your research, please consider citing:

@misc{zhou2026caprunerconceptualadjacentscenegraph,
      title={CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models}, 
      author={Shengli Zhou and Xiangchen Wang and Guanhua Chen and Feng Zheng},
      year={2026},
      eprint={2606.07529},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.07529}, 
}