Wu, Huimin, Kwang-Ting Cheng, Stephen Lin, and Zhirong Wu. “A Study of Finetuning Video Transformers for Multi-View Geometry Tasks”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 13 (March 14, 2026): 10646–10654. Accessed June 1, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/38038.