You are here
Publications
"Breaking Memory Wall for Fast Edge LLM Inference Using Contextual Sparsity",
IEEE Transactions on Mobile Computing, 06/2026.
"Task Scheduling for Heterogeneous HardwareCo-Inference in IoT-Edge-Cloud Continuum",
Chinese Journal of Electronics, vol. 35, issue 4, pp. 1-12, 07/2026.
]