One paper has been accepted by ACL 2026!
CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models
- Shengli Zhou, Xiangchen Wang, Guanhua Chen, and Feng Zheng✉
- Accepted by ACL 2026 (Main Conference): Code (GitHub)
- Existing scene graph pruning for 3D vision-language tasks often discards task-critical relations, harming spatial reasoning. To address this issue, we propose CAPruner, which combines semantic relevance and spatial proximity to estimate relation importance under specific task context, trained without expensive relation-level annotations. Experiments show it preserves key spatial relations and significantly boosts LLM performance on 3D-VL tasks.
- Title: One paper has been accepted by ACL 2026!
- Author: Shengli Zhou
- Created at : 2026-04-06 22:06:00
- Updated at : 2026-04-06 23:47:04
- Link: https://fz-zsl.github.io/ACL2026/
- License: This work is licensed under CC BY-NC-SA 4.0.