Guo, Tianyu, Shanwei Zhao, Shiai Zhu, and Chenguang Ma. “SPEED-Q: Staged Processing With Enhanced Distillation Towards Efficient Low-Bit On-Device VLM Quantization”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 26 (March 14, 2026): 21486–21494. Accessed May 25, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/39296.