GUO, Tianyu; ZHAO, Shanwei; ZHU, Shiai; MA, Chenguang. SPEED-Q: Staged Processing with Enhanced Distillation Towards Efficient Low-Bit On-Device VLM Quantization. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 26, p. 21486–21494, 2026. DOI: 10.1609/aaai.v40i26.39296. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39296. Acesso em: 25 may. 2026.