Algorithm/Software

FastQuery: Communication-efficient Embedding Table Query for Private LLMs inference
Chenqi Lin, Tianshi Xu, Zebin Yang, 李萌, Runsheng Wang, Ru Huang
论文
CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference
A network–protocol co-optimization framework for reducing the communication overhead of secure private inference.
Wenxuan Zeng, 李萌, Haichuan Yang, Wen-Jie Lu, Runsheng Wang, Ru Huang
论文
Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inference
Tianshi Xu, 李萌, Runsheng Wang, Ru Huang
论文
Memory-aware Scheduling for Complex Wired Networks with Iterative Graph Optimization
Shuzhang Zhong, 李萌, Yun (Eric) Liang, Runsheng Wang, Ru Huang
论文
MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention
Wenxuan Zeng, 李萌, Wenjie Xiong, Tong Tong, Wen-Jie Lu, Jin Tan, Runsheng Wang, Ru Huang
论文
AVATAR: An Aging- and Variation-Aware Dynamic Timing Analyzer for Error-Efficient Computing
Zuodong Zhang, Zizheng Guo, Yibo Lin, 李萌, Runsheng Wang, Ru Huang
论文
BiT: Robustly Binarized Multi-distilled Transformer
Zechun Liu, Barlas Oguz, Aasish Pappu, Lin Xiao, Scott Yih, 李萌, Raghuraman Krishnamoorthi, Yashar Mehdad
论文
Depth Shrink: Empowering Hardware-Friendly Shallow Neural Networks
Yonggan Fu, Haichuan Yang, Jiayi Yuan, 李萌, Raghuraman Krishnamoorthi, Vikas Chandra, Yingyan Lin
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