AdaRadar: AdaRadar: Rate Adaptive Spectral Compression for Radar-based Perception

We propose radar data compression with adaptive feedback. It dynamically adjusts the compression ratio by performing gradient descent from the proxy gradient of detection confidence with respect to the compression rate. Validated on the RADIal, CARRADA, and Radatron datasets, the AdaRadar achieves over 100x feature size reduction at minimal performance drop (1%p). The project page is HERE.

UL-VIO: Ultra-lightweight Visual-Inertial Odometry with Noise Robust Test-time Adaptation

We propose UL-VIO – an ultra-lightweight (<1M) VIO network capable of test-time adaptation (TTA) based on visual-inertial consistency. The project page is HERE.

Digital Low-Dropout Voltage Regulator (DLDO) Survey

We open-source the exel spreadsheet that surveys the digital low-dropout voltage regulators (digital LDO or DLDO) published in 2010-present. We plan to update the survey roughly yearly basis. We also publish an conference article on the review and benchmark of the DLDOs, which helps to understand the survey process. You can find the survey spreadsheet HERE and the paper HERE.