Yuji Chai

Bigger&Faster: Two-stage Neural Architecture Search for Quantized Transformer Models

Glenn G. Ko, Yunho Jin, Yuji Chai, 2022, ArXiv.

FlexGibbs: Reconfigurable Parallel Gibbs Sampling Accelerator for Structured Graphs

Rob A. Rutenbar, Gu-Yeon Wei, David Brooks, 2019, 2019 IEEE 27th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM).

A 16-nm SoC for Noise-Robust Speech and NLP Edge AI Inference With Bayesian Sound Source Separation and Attention-Based DNNs

Alexander M. Rush, Glenn G. Ko, Gu-Yeon Wei, 2023, IEEE Journal of Solid-State Circuits.

PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices

D. Brooks, P. Whatmough, Dibakar Gope, 2023, ArXiv.

INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation

Glenn G. Ko, D. Brooks, Gu-Yeon Wei, 2023, ArXiv.

SpeedLimit: Neural Architecture Search for Quantized Transformer Models

Glenn G. Ko, D. Brooks, Gu-Yeon Wei, 2022, 2209.12127.

9.8 A 25mm2 SoC for IoT Devices with 18ms Noise-Robust Speech-to-Text Latency via Bayesian Speech Denoising and Attention-Based Sequence-to-Sequence DNN Speech Recognition in 16nm FinFET

Alexander M. Rush, Gu-Yeon Wei, David Brooks, 2021, 2021 IEEE International Solid- State Circuits Conference (ISSCC).

SpeedLimit: Neural Architecture Search for Quantized Transformer Models

Glenn G. Ko, D. Brooks, Gu-Yeon Wei, 2022, 2209.12127.