Y
Yuan Xie
Researcher at University of California, Santa Barbara
Publications - 794
Citations - 32484
Yuan Xie is an academic researcher from University of California, Santa Barbara. The author has contributed to research in topics: Computer science & Cache. The author has an hindex of 76, co-authored 739 publications receiving 24155 citations. Previous affiliations of Yuan Xie include Pennsylvania State University & Foundation University, Islamabad.
Papers
More filters
Proceedings ArticleDOI
Predicting the Output Structure of Sparse Matrix Multiplication with Sampled Compression Ratio
Zhaoyang Du,Yijin Guan,Tianchan Guan,Dimin Niu,Nianxiong Nick Tan,Xiaopeng Yu,Hongzhong Zheng,Jianyi Meng,Xiaolang Yan,Yuan Xie +9 more
TL;DR: A novel sampling-based method with better accuracy and low costs compared to the existing sampling- based method, which predicts the compression ratio of SpGEMM and the predicted output structure is obtained by dividing the FLOP per output row by the predicted compression ratio.
Journal ArticleDOI
What is 3D IC and what are the design challenges for 3D ICs
TL;DR: Three-dimensional integrated circuits (3D ICs) are the IC chips with multiple device layers stacked together with various vertical interconnect technologies that could be connected with wire-bonding, through-silicon-vias, microbump, or even inductive/capacitive contact.
Proceedings ArticleDOI
Toward Robust Spiking Neural Network Against Adversarial Perturbation
TL;DR: This work designs S-IBP and S-CROWN that tackle the non-linear functions in SNNs’ neuron modeling, and formalizes the boundaries for both digital and spike inputs, and demonstrates the efficiency of the proposed robust training method in different datasets and model architectures.
Proceedings ArticleDOI
Blind Separation of Heart Sound Convolutive Mixtures Utilizing Independent Vector Analysis
Yuan Xie,Kan Xie,Xie Shengli +2 more
TL;DR: In this article, an optimization convolutive blind source separation algorithm utilizing independent vector analysis is proposed for separation of the heart sound mixtures, where a denoising approach is firstly used to reduce the impact of the additive white Gaussian noise, and then the mixing signals in time domain are transmitted into the frequency domain.
Journal ArticleDOI
Survival outcome of patients with relapsed or refractory classical Hodgkin lymphoma who achieved remission during immune checkpoint inhibitors treatment.
TL;DR: Deeper remission and longer duration and led to favorable survival outcome for patients with relapsed or refractory classical Hodgkin lymphoma who achieved remission during ICIs treatment.