Zhan, Junfei, Haoxun Shen, Zheng Lin, and Tengjiao He. 2026. “PRISM: Privacy-Aware Routing for Adaptive Cloud–Edge LLM Inference via Semantic Sketch Collaboration”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (33):28150-58. https://doi.org/10.1609/aaai.v40i33.40041.