On-device learning is a promising technique for emerging privacy-preserving machine
learning paradigms. However, through quantitative experiments, we find that commodity …

Large foundation models, including large language models (LLMs), vision transformers
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …

This paper proposes Mandheling, the first system that enables highly resource-efficient on-
device training by orchestrating mixed-precision training with on-chip Digital Signal …

Deploying deep learning (DL) on mobile devices has been a notable trend in recent years.
To support fast inference of on-device DL, DL libraries play a critical role as algorithms and …

In today's landscape, smartphones have evolved into hubs for hosting a multitude of deep
learning models aimed at local execution. A key realization driving this work is the notable …

Currently, most reliable and commercialized artificial pancreas systems for type 1 diabetes
are hybrid closed-loop systems, which require the user to announce every meal and its size …

To preserve user privacy while enabling mobile intelligence, techniques have been
proposed to train deep neural networks on decentralized data. However, training over …

As a critical and prevalent service in future mobile networks, virtual reality (VR) is latency-
sensitive and power-hungry, bringing out the optimization problem of trade-off among power …

Multi-modal neural networks have become increasingly pervasive in many machine learning
application domains due to their superior accuracy by fusing various modalities. However …

Deep Learning (DL) is increasingly being integrated into Web applications through a
method known as" in-browser inference", where the DL processes occur directly within Web …