Guo, Tianyu, et al. “SPEED-Q: Staged Processing With Enhanced Distillation Towards Efficient Low-Bit On-Device VLM Quantization”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 26, Mar. 2026, pp. 21486-94, doi:10.1609/aaai.v40i26.39296.