Xi Ye

Xi Ye

Auto-generated profile, based on publicly available information

Xi Ye

♢ The University of Texas at Austin, ♠ Salesforce AI

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 June 2022 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
WYWeikai Yang
Weikai Yang
XYXi Ye
Xi Ye
XZXingxing Zhang
Xingxing Zhang
LXLanxi Xiao
Lanxi Xiao
JXJiazhi Xia
Jiazhi Xia
SLShixia Liu
Shixia Liu
The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes and make improvements. To tackle this issue, we propose a visual analysis method, FSLDiagnotor. Given a set of base learners and a collection of samples with a few shots, we consider two problems: 1) finding a subset of base learners that well predict the sample collections; and 2) replacing the low-quality shots with more representative ones to adequately represent the sample collections. We formulate both problems as sparse subset selection and develop two selection algorithms to recommend appropriate learners and shots, respectively. A matrix visualization and a scatterplot are combined to explain the recommended learners and shots in context and facilitate users in adjusting them. Based on the adjustment, the algorithm updates the recommendation results for another round of improvement. Two case studies are conducted to demonstrate that FSLDiagnotor helps build a few-shot classifier efficiently and increases the accuracy by 12% and 21%, respectively.

1 January 2020
Verified
Conference Paper
Open access
PDF file
XYXi Ye
Xi Ye
QCQiaochu Chen
Qiaochu Chen
IDIsil Dillig
Isil Dillig
GDGreg Durrett
Greg Durrett
Xi Ye, Qiaochu Chen, Isil Dillig, Greg Durrett. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.

29 November 2021
Verified
Conference Paper
Closed access
PDF file
LYLinWen Yu
LinWen Yu
TQTongHui Qian
TongHui Qian
XYXi Ye
Xi Ye
FZFang Zhou
Fang Zhou
ZLZhigang Luo
Zhigang Luo
AZAo Zou
Ao Zou
As a new type of water operation platform in recent years, surface unmanned boats have gradually become a hotspot for many scholars to study. The path planning capability of unmanned boat is an important measure of the intelligence degree of unmanned boat. To address the obstacle avoidance problem of surface autonomous unmanned boat path planning, this paper proposes a global path planning method for surface autonomous unmanned boats based on the improved grid method by modeling the known water environment with a grid method. In order to accurately simulate the impact of obstacles on the path planning of surface autonomous unmanned boats due to the drifting effect, this paper simulates the drifting increment of obstacles on the water surface by setting different obstacle forms and sizes, and conducts a MATLAB simulation platform to simulate the drifting increment of obstacles on the water surface. The simulation experiments prove the real reliability of the improved obstacle avoidance strategy algorithm proposed in the main paper.

1 July 2016
Verified
Conference Paper
Closed access
YYYida Ye
Yida Ye
Zongxiang LuZongxiang Lu
Zongxiang Lu
YQYing Qiao
Ying Qiao
XYXi Ye
Xi Ye
WHWei Hu
Wei Hu
LWLinlin Wu
Linlin Wu
The increasing penetration of new variable generations in power systems necessitates the modeling of the stochastic and variable characteristics, especially the modeling of wind power forecast error. A conditional probabilistic dependent method of modeling wind power forecast error of one single wind farm and multiple wind farms is presented in this paper, providing a range of potential forecast error for a given confidence level. Furthermore, a distribution generation algorithm of power forecast error based on Monte Carlo algorithm and genetic algorithm is proposed by applying the historical data and rank correlation of forecast error in multiple wind farms. Finally, the proposed method is verified in the case study by comparison of the conditional probabilistic model and the unconditional probabilistic model.

1 January 2023
Verified
Conference Paper
Open access
PDF file
PSPrasann Singhal
Prasann Singhal
JXJiacheng Xu
Jiacheng Xu
XYXi Ye
Xi Ye
GDGreg Durrett
Greg Durrett
Prasann Singhal, Jiacheng Xu, Xi Ye, Greg Durrett. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

9 January 2022
Verified
Conference Paper
Closed access
YXYe Xi
Ye Xi
ZGZhejun Guo
Zhejun Guo
LWLongchun Wang
Longchun Wang
QXQingda Xu
Qingda Xu
TRTao Ruan
Tao Ruan
JLJingquan Liu
Jingquan Liu
This paper reports a method of fabricating the fabricating the 3D paper-based microfluidic device using atmospheric pressure low temperature plasma jet, which can achieve direct writing and maskless machining by programming the motion path of the three-axis moving platform. The depth and width of the microchannel processed by this method can be adjusted and two liquid channels and through holes can be prepared on a single layer filter paper to realize a three-dimensional paper-based device. Compared with stacking and folding, this method can ensure the alignment accuracy between functional layers of 3D microfluidic devices and reduce the difficulty and time of preparation