@inproceedings{karki-etal-2026-reading, title = "Reading Between the Layers: Cross-Modal Alignment and Representational Hierarchy in Vision Transformers", author = "Karki, Sugam and V{\'a}zquez, Ra{\'u}l and Kementchedjhieva, Yova", editor = "Zhang, Yue and Xu, Ruifeng and Purwarianti, Ayu and Rong, Tong and Suzuki, Jun", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026", month = nov, year = "2026", address = "Hengqin, China", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.findings-aacl.242/", pages = "4761--4775", ISBN = "979-8-89176-444-6" }