Han Zhang @hanzhang.bsky.social · 09/09/2026A classic demonstration of human goal-directed attention is provided by Yarbus, where observers show distinct eye movement patterns depending on the goal. 100
Han Zhang @hanzhang.bsky.social · 09/09/2026Here, across thousands of naturalistic scenes, I tested whether VLMs show similar behavior, and indeed they do. Furthermore, model predictions aligned more closely with human fixations under matching goals than under mismatched goals. 100
Han Zhang @hanzhang.bsky.social · 09/09/2026This alignment also shows in decoder-layer attention and intermediate thinking traces. Search thinking is semantically close to the target (a [bottle] could be near the table, under the table, behind the dishes), whereas free-view thinking is close to visual prominence. 110
