3 papers
cs.CV2026
DynaFilter: Cloud-driven Dynamic Filtering for Satellite Edge Intelligence
Ziyang Zhang, Jie Liu, Luca Mottola
Modern satellite edge systems, including those performing remote sensing tasks such object detection and tracking, are characterized by severely limited bandwidth and intermittent…
cs.LG2026
SparseDVFS: Sparse-Aware DVFS for Energy-Efficient Edge Inference
Ziyang Zhang, Zheshun Wu, Jie Liu +1
Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for ene…
cs.DC2025
SparOA: Sparse and Operator-aware Hybrid Scheduling for Edge DNN Inference
Ziyang Zhang, Jie Liu, Luca Mottola
The resource demands of deep neural network (DNN) models introduce significant performance challenges, especially when deployed on resource-constrained edge devices. Existing solut…