Lingkun Meng
Papers
1
Total Citations
1
H-Index
1
About
Lingkun Meng is a researcher at the forefront of edge computing and adaptive inference systems, with a focus on optimizing the performance of online AI pipelines in resource-constrained environments. Their most notable contribution, "Adaptive scheduling of online inference pipelines at the edge: A post-hoc request-oriented approach" (2025), introduces a novel framework that dynamically adjusts scheduling strategies based on real-time request characteristics, significantly improving latency and throughput for edge-based machine learning inference. This work addresses a critical bottleneck in deploying AI at the network edge, where computational resources are limited and demand fluctuates unpredictably. While early in its impact, the paper's innovative post-hoc approach—which reorders and prioritizes inference tasks after initial processing—has already garnered attention for its practical applicability in IoT and smart city systems. Meng's research bridges the gap between theoretical scheduling algorithms and real-world deployment challenges, offering scalable solutions for latency-sensitive applications. Their work is particularly relevant for students and engineers designing efficient edge AI systems, as it provides a blueprint for balancing accuracy, speed, and resource usage in dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1