most citedDocument Intelligence in the Era of Large Language Models: A Survey

2 citations · 2 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Visual Attention Faithfulness in Vision-Language Models is Heterogeneous

Xurui Song, Weishi Wang, Zhongqi Yue +5

Whether attention weights faithfully reflect model reasoning has been actively debated in NLP, yet this question remains largely unexplored for the visual modality in Vision-Langua…