Algorithm/Software

Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with …
Haichuan Yang, Yuan Shangguan, Dilin Wang, 李萌, Pierce Chuang, Xiaohui Zhang, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra
论文
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
论文
SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems
We design deep neural networks (DNNs) and corresponding networks’ splittings to distribute DNNs’ workload to camera sensors …
Xin Dong, Ziyun Li, 李萌, Zhongnan Qu, Barbara De Salvo, Chiao Liu, Hsiang-Tsung Kung
论文
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training
通过梯度冲突感知的超网络训练搜索高效视觉 Transformer。
Chengyue Gong, Dilin Wang, 李萌, Xinlei Chen, Zhicheng Yan, Yuandong Tian, Qiang Liu, Vikas Chandra
论文
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
论文
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
通过注意力采样提升权重共享神经网络架构搜索在不同计算预算下的表现。
Dilin Wang, 李萌, Chengyue Gong, Vikas Chandra
论文
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
论文
TimingSAT: Decamouflaging timing-based logic obfuscation
In order to counter advanced reverse engineering techniques, various integrated circuit (IC) camouflaging methods are proposed to …
李萌, Kaveh Shamsi, Yier Jin, David Z Pan
论文
Federated Learning with Non-IID Data
Federated learning enables resource-constrained edge compute devices, such as mobile phones and IoT devices, to learn a shared model …
Yue Zhao, 李萌, Liangzhen Lai, Naveen Suda, Damon Civin, Vikas Chandra
论文
PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training
Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and …
李萌, Liangzhen Lai, Naveen Suda, Vikas Chandra, David Z. Pan
论文