Fu, Teng, Mengyang Zhao, Ke Niu, Kaixin Peng, and Bin Li. “OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and Understanding”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 5 (March 14, 2026): 4031–4039. Accessed May 27, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/37406.