@inproceedings{ye-etal-2025-beyond, title = "Beyond End-to-End {VLM}s: Leveraging Intermediate Text Representations for Superior Flowchart Understanding", author = "Ye, Junyi and Dash, Ankan and Yin, Wenpeng and Wang, Guiling", editor = "Chiruzzo, Luis and Ritter, Alan and Wang, Lu", booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", month = apr, year = "2025", address = "Albuquerque, New Mexico", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.180/", pages = "3534--3548", ISBN = "979-8-89176-189-6" }