Preprint
Oct 2026
From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models
Predicting future spatial states supports collision avoidance and timely decision-making in dynamic environments. However, existing vision-language models (VLMs) and benchmarks for spatial reasoning primarily focus on observed scenes, leaving predictive spatial reasoning beyond the observed interval underexplored. To t...
Fei-Ran Wang, Xiao-Qi Wang, Zi-Wei Li et al.
· 0 citations