1

READ: Reliability-Enhanced Accelerator Dataflow Optimization using Critical Input Pattern Reduction
Zuodong Zhang, 李萌, Yibo Lin, Runsheng Wang, Ru Huang
BiT: Robustly Binarized Multi-distilled Transformer
Zechun Liu, Barlas Oguz, Aasish Pappu, Lin Xiao, Scott Yih, 李萌, Raghuraman Krishnamoorthi, Yashar Mehdad
Depth Shrink: Empowering Hardware-Friendly Shallow Neural Networks
Yonggan Fu, Haichuan Yang, Jiayi Yuan, 李萌, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network …
Jiaqi Gu, Hyoukjun Kwon, Dilin Wang, Wei Ye, 李萌, Yu-Hsin Chen, Liangzhen Lai, Vikas Chandra, David Pan
DNA: Differentiable Network-Accelerator Co-Search
Powerful yet complex deep neural networks (DNNs) have fueled a booming demand for efficient DNN solutions to bring DNN-powered …
Yongan Zhang, Yonggan Fu, Weiwen Jiang, Chaojian Li, Haoran You, 李萌, Vikas Chandra, Yingyan Lin
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. …
Dilin Wang, Chengyue Gong, 李萌, Qiang Liu, Vikas Chandra
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and …
Dilin Wang, 李萌, Chengyue Gong, Vikas Chandra
Improving efficiency in neural network accelerator using operands hamming distance optimization
Neural network accelerator is a key enabler for the on-device AI inference, for which energy efficiency is an important metric. The …
李萌, Yilei Li, Vikas Chandra
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically …
Chengyue Gong, Dilin Wang, 李萌, Vikas Chandra, Qiang Liu
Co-exploration of neural architectures and heterogeneous asic accelerator designs targeting multiple tasks
Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and …
Lei Yang, Zheyu Yan, 李萌, Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra, Weiwen Jiang, Yiyu Shi