GitHub

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

1.0 and 2.0: relevant code archived in the sub directory v1. You can pip install timesfm==1.3.0 to install an older version of this package to load them.
GitHub

Python script to automate Mi Community unlock request at 00:00 beijing time via ADB

On newer global HyperOS devices, Xiaomi has implemented another unlock step for unlocking the bootloader via the Mi Community app. However, there is a daily quota of devices that can be unlocked per ...
IEEE

A 28nm PVT Inner-Tracking Time-Domain Compute-InMemory Macro Featuring Scalable Global Timer and Reconfigurable Pipelined Cascading for Edge-Al Devices

Abstract: Compute-in-memory (CIM) is gaining popularity in edge-AI applications due to its ability to integrate multiply-accumulate (MAC) operations directly with memory. Voltage-domain CIMs [1–4] ...
IEEE

A Real-Time Machine Learning Module for Motion Artifact Detection in fNIRS

Abstract: Functional Near-Infrared Spectroscopy (fNIRS) is a neuroimaging method which can be implemented with a wearable form factor. However, the data of fNIRS can be affected by motion artifact, ...