ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
Yiming Zhang, Jiacheng Chen, Jiaqi Tan, Yongsen Mao, Wenhu Chen, Angel X. Chang
š arxiv.org/abs/2604.24300
š 3dlg-hcvc.github.io/revsi/
arxiv.org
Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings. First, many benchmarks derive question-answer (QA) pairs from point-cloud-b...
