Mengwei Xu

This survey discusses making AI models more efficient and sustainable.

LLMs are set to improve privacy and functionality on mobile devices.

A look at the CAP principle and its impact on large language models.

New inference system improves speed and efficiency of on-device LLMs.

A new approach for flexible mobile AI using on-device language models.

A new system enhances information retrieval on mobile devices with efficiency and speed.

Small language models are changing how technology works in everyday devices.