作者位次 #5/9ACL 2026Findings· Findings of ACL
Can LLM s See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions
Zhongbin Guo · Zhen Yang · Yushan Li · Xinyue Zhang · Wenyu Gao · Jiacheng Wang · Chengzhi Li · Xiangrui Liu · Ping Jian
摘要
Recent advancements in Spatial Intelligence (SI) have predominantly relied on Vision-Language Models (VLMs), yet a critical question remains: does spatial understanding originate from visual encoders or the fundamental reasoning backbone? Inspired by this question, we introduce SiT-Bench , a nove...