collaborators

5 papers

cs.LG2026

MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression

Sheng Qiang, Ruiwei Chen, Yinpeng Wu +5

Long-context LLM services now sustain prompts with hundreds of thousands to millions of tokens, making the key-value (KV) cache a first-order serving cost. Because the cache grows…

cs.CR2026

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

Yinpeng Wu, Yitong Chen, Lixiang Wang +3

Device-side Large Language Models (LLMs) have grown explosively, offering stronger privacy and higher availability than their cloud-side counterparts. During LLM inference, both th…

cs.CR2026

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

Yinpeng Wu, Yitong Chen, Lixiang Wang +3

Device-side Large Language Models (LLMs) have witnessed explosive growth, offering higher privacy and availability compared to cloud-side LLMs. During LLM inference, both model wei…

cs.RO2026

Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment

Kaijun Zhou, Qiwei Chen, Da Peng +3

Vision-Language-Action (VLA) models are promising for generalist robot control, but on-robot deployment is bottlenecked by real-time inference under tight cost and energy budgets.…

cs.CR2025

TZ-LLM: Protecting On-Device Large Language Models with Arm TrustZone

Xunjie Wang, Jiacheng Shi, Zihan Zhao +3

Large Language Models (LLMs) deployed on mobile devices offer benefits like user privacy and reduced network latency, but introduce a significant security risk: the leakage of prop…