5 papers
FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
Hetvi Shastri, Pragya Sharma, Walid A. Hanafy +2
Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-se…
LLM-Driven Auto Configuration for Transient IoT Device Collaboration
Hetvi Shastri, Walid A. Hanafy, Li Wu +3
Today's Internet of Things (IoT) has evolved from simple sensing and actuation devices to those with embedded processing and intelligent services, enabling rich collaborations betw…
MEL: Multi-level Ensemble Learning for Resource-Constrained Environments
Krishna Praneet Gudipaty, Walid A. Hanafy, Kaan Ozkara +4
AI inference at the edge is becoming increasingly common for low-latency services. However, edge environments are power- and resource-constrained, and susceptible to failures. Conv…
FailLite: Failure-Resilient Model Serving for Resource-Constrained Edge Environments
Li Wu, Walid A. Hanafy, Tarek Abdelzaher +3
Model serving systems have become popular for deploying deep learning models for various latency-sensitive inference tasks. While traditional replication-based methods have been us…
CarbonEdge: Leveraging Mesoscale Spatial Carbon-Intensity Variations for Low Carbon Edge Computing
Li Wu, Walid A. Hanafy, Abel Souza +5
The proliferation of latency-critical and compute-intensive edge applications is driving increases in computing demand and carbon emissions at the edge. To better understand carbon…