Qifei Dong

Mr. Qifei Dong

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 February 2024
Verified
Conference Paper
Open access
QDQifei Dong
Qifei Dong
XCXiangliang Chen
Xiangliang Chen
MSMahadev Satyanarayanan
Mahadev Satyanarayanan
Cyber-human and cyber-physical systems have tight end-to-end latency bounds, typically on the order of a few tens of milliseconds. In contrast, cloud-based large-language models (LLMs) have end-to-end latencies that are two to three orders of magnitude larger. This paper shows how to bridge this large gap by using LLMs as offline compilers for creating task-specific code that avoids LLM accesses. We provide three case studies as proofs of concept, and discuss the challenges in generalizing this technique to broader uses.

3 December 2025
Verified
Conference Paper
Open access
QDQifei Dong
Qifei Dong
JXJingao Xu
Jingao Xu
PPPadmanabhan Pillai
Padmanabhan Pillai
MSMahadev Satyanarayanan
Mahadev Satyanarayanan

17 October 2024 in Electronics
Verified
Journal Article
Open access
PDF file
RIRoger Iyengar
Roger Iyengar
QDQifei Dong
Qifei Dong
CNChanh Nguyen
Chanh Nguyen
PPPadmanabhan Pillai
Padmanabhan Pillai
MSMahadev Satyanarayanan
Mahadev Satyanarayanan
Edge computing has much lower elasticity than cloud computing because cloudlets have much smaller physical and electrical footprints than a data center. This hurts the scalability of applications that involve low-latency edge offload. We show how this problem can be addressed by leveraging the growing sophistication and compute capability of recent wearable devices. We investigate four Wearable Cognitive Assistance applications on three wearable devices, and show that the technique of offload shaping can significantly reduce network utilization and cloudlet load without compromising accuracy or performance. Our investigation considers the offload shaping strategies of mapping processes to different computing tiers, gating, and decluttering. We find that all three strategies offer a significant bandwidth savings compared to transmitting full camera images to a cloudlet. Two out of the three devices we test are capable of running all offload shaping strategies within a reasonable latency bound.

23 June 2025
Verified
Conference Paper
Open access
JXJingao Xu
Jingao Xu
MBMihir Bala
Mihir Bala
TEThomas Eiszler
Thomas Eiszler
XCXiangliang Chen
Xiangliang Chen
QDQifei Dong
Qifei Dong
MSMahadev Satyanarayanan
Mahadev Satyanarayanan

20 June 2026
Verified
Conference Paper
Open access
QDQifei Dong
Qifei Dong
JXJingao Xu
Jingao Xu
PPPadmanabhan Pillai
Padmanabhan Pillai
RKRoberta Klatzky
Roberta Klatzky
MSMahadev Satyanarayanan
Mahadev Satyanarayanan

28 February 2024
Verified
Conference Paper
Open access
QDQifei Dong
Qifei Dong
XCXiangliang Chen
Xiangliang Chen
MSMahadev Satyanarayanan
Mahadev Satyanarayanan
This poster is based on the accepted submission to HotMobile2024: Creating Edge AI from Cloud-based LLMs.