4 papers
BitFair: A 12-nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Vision
Ang Li, Chang Gao
Extended Reality (XR) wearables require always-on perception within tight power envelopes of a few watts and motion-to-photon latency budgets below 20 ms, leaving only a few millis…
OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion
Yizhuo Wu, Ang Li, Chang Gao
Neural network (NN)-based Digital Predistortion (DPD) improves linearization for wideband radio frequency (RF) power amplifiers (PAs) but often increases the complexity of the digi…
JaneEye: A 12-nm 2K-FPS 18.9-J/Frame Event-based Eye Tracking Accelerator
Tao Han, Ang Li, Qinyu Chen +1
Eye tracking has become a key technology for gaze-based interactions in Extended Reality (XR). However, conventional frame-based eye-tracking systems often fall short of XR's strin…
DPD-NeuralEngine: A 22-nm 6.6-TOPS/W/mm Recurrent Neural Network Accelerator for Wideband Power Amplifier Digital Pre-Distortion
Ang Li, Haolin Wu, Yizhuo Wu +3
The increasing adoption of Deep Neural Network (DNN)-based Digital Pre-distortion (DPD) in modern communication systems necessitates efficient hardware implementations. This paper…