← back to paper

Review history

arxiv: 2508.21565 · 2 revisions

How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   106821 ms 11763 in 13078 out 2026-08-15T16:39:29.274432+00:00
2. 2026-08-05 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   91070 ms 11737 in 9249 out 2026-08-05T14:10:52.376756+00:00