2 papers
cs.NI2026
Delay-Adaptive Speculation Control for Low-Latency Edge-Cloud LLM Inference
Kangkang Sun, Jianhua Li, Xiuzhen Chen +2
Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens and a larger target model to verify them in parallel. In…
cs.NI2026
Safety-Aware AoI Scheduling for LEO Satellite-Assisted Autonomous Driving
Kangkang Sun, Junyi He, Juntong Liu +3
Autonomous platoons traversing infrastructure gaps increasingly depend on LEO satellite backhaul for safety-critical updates, yet no existing framework jointly addresses compound D…