VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes 文章

ArXiv CS.CV2026-05-26NEWSen作者: Paul Gavrikov, Wei Lin, M. Jehanzeb Mirza, Soumya Jahagirdar, Muhammad Huzaifa, Sivan Doveh, Serena Yeung-Levy, James Glass, Hilde Kuehne
查看原文 →
关系图谱

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes · 相关技术

相关技术

ORMODEPLAdivide-and-conquer partitioningVisual Question Answering (VQA)VQAStanPROBEOWLOTANLIVLMForFOLDenseASICANN