Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding

Lecture notes in computer science 2026 Open access

Read full text

Authors: Na An, Inha Kang, Minhyun Lee, Hyunjung Shim

DOI: 10.1007/978-3-032-37350-2_21

Cited by: 0

Fields of Study & Subjects

Advanced Image and Video Retrieval Techniques Image Retrieval and Classification Techniques AI in cancer detection