Natural language processing (NLP) sees rich mobile applications. To supp...
Transformer-based pre-trained models have become the de-facto solution f...
As model finetuning is central to the modern NLP, we set to maximize its...
Natural Language Processing (NLP) inference is seeing increasing adoptio...
A TrustZone TEE often invokes an external filesystem. While filedata can...
Transformer-based pre-trained models have revolutionized NLP for superio...
We present a holistic design for GPU-accelerated computation in TrustZon...
While TrustZone can isolate IO hardware, it lacks drivers for modern IO
...
TinyStack is a novel way for deploying GPU-accelerated computation on mo...
Running neural networks (NNs) on microcontroller units (MCUs) is becomin...
Object re-identification (ReID) is a key application of city-scale camer...
A set of about 80 researchers, practitioners, and federal agency program...
Surveillance IoT cameras are becoming autonomous: they operate on batter...
As low-cost surveillance cameras grow rapidly, we advocate for these cam...
Smart devices produce security-sensitive data and keep them in on-device...
Stream analytics have an insatiable demand for memory and performance.
E...
Smart devices see a large number of ephemeral tasks driven by background...
Modern mobile and embedded platforms see a large number of ephemeral tas...
We are in the dawn of deep learning explosion for smartphones. To bridge...
Deep learning (DL) is a game-changing technique in mobile scenarios, as
...
We present VStore, a data store for supporting fast, resource-efficient
...
We present a data store managing large videos for retrospective analytic...
While it is compelling to process large streams of IoT data on the cloud...
We present StreamBox-TZ, a stream analytics engine for an edge platform....
Convolutional Neural Network (CNN) is the state-of-the-art algorithm of ...
Sensing on smartphones is known to be power-hungry. It has been shown th...