Xuxin Tang

Human-AI Interaction Researcher

Hello!👋 I am a Computer Science PhD student at the Sanghani Center for Artificial Intelligence & Data Analytics at Virginia Tech. My advisor is Prof. Chris North. During my first year, I was advised by Prof. Yalong Yang. Prior to joining Virginia Tech, I had nearly three years of industry experience, first working as a full-stack development engineer and later as a machine learning engineer on large-scale recommendation systems. I earned both my B.S. and M.S. degrees from Wuhan University, where I was mentored by Prof. Zhijiang Li and Dr. Fan Zhang. During my M.S., I also visited and collaborated with Prof. Xiu Li from Tsinghua University.

My research interest lies in the intersection of Visualization, Human-Computer Interaction, and Artificial Intelligence, where I use visual analytics and human-in-the-loop methods to design, build, and evaluate human-AI collaborative systems to enhance the efficiency, trustworthiness, and transparency of AI models.

I am looking for internship positions for summer 2025. With experience in human-AI collaboration and large language models, I am excited to apply my skills in a dynamic environment. If your organization is seeking a dedicated and passionate intern, I’d love to connect!

Google Scholar/Twitter/LinkedIn

News

Oct 30, 2024	Exited to present my research on visual analytics and human-LLM collaboration to Bloomberg UX Research Group!
Sep 9, 2024	Our paper “Steering LLM Summarization with Visual Workspaces for Sensemaking” accepted to IEEE NLVIZ Workshop 2024.
Apr 12, 2024	Passed my PhD qualifier exam.
Jun 6, 2023	Visited HCIE Group at CSAIL, MIT as a visiting PhD student, working with Prof. Stefanie Mueller, Mustafa Doga Dogan, and Martin Feick. Fun work coming soon!
Aug 15, 2022	Begin my doctoral studies at Virginia Tech.

Selected Publications

2024

Steering LLM Summarization with Visual Workspaces for Sensemaking

Xuxin Tang, Eric Krokos, Can Liu, and 4 more authors

IEEE VIS NLVIZ Workshop 2024, 2024

HTML

2017

Quantifying Cloud Elasticity with Container-Based Autoscaling

Xuxin Tang, Fan Zhang, Xiu Li, and 2 more authors

15th Intl Conf on Pervasive Intelligence and Computing (PICom 2017), 2017

Abs HTML

Containers have been a pervasive approach to help rapidly develop, test and update the Internet of Things applications (IoT). The autoscaling of containers can adaptively allocate computing resources for various data volumes over time. Therefore, elasticity, a critical feature of a cloud platform, is significant to measure the performance of lightweight containers. In this paper, we propose a framework with container auto-scaler. It monitors containers resource usage and accordingly scales in or scales out containers in need. Further, we define elasticity mathematically in order to quantify the cloud elasticity using the proposed framework. Extensive experiments are carried out with different workload modes, workload durations, and scaling cool- down period of times. Experiment results show that the framework captures the workload variation firmly with a very short delay. We also find out that the cloud platform shows the best elasticity in repeat workload mode due to its recurring and predictable feature. Finally, we discover the length of the cool- down period should be properly set up in order to balance system stability and good elasticity.
A night image enhancement algorithm based on guided filtering

Xuxin Tang, Zhijiang Li, and Yuhang Chen

Advanced Graphic Communications and Media Technologies, 2017

Abs HTML

Colored night images lead to various problems in real life, such as low dynamic range, detail blurring and so on, which are waiting to be solved. For this reason, it proposes an algorithm for night image enhancement based on guided filtering in the paper. This image process includes three main steps. Firstly, by transforming to HVS color space, the targeted image is separated coarsely into two images—base layer image and detail layer image in the result of guided filtering. In the second step, the base layer and detail layer are processed by different strategies selectively and respectively to lighten the whole, but remain details as much as possible. Eventually, the base layer, which has been previously increased contrast, is added detail layer to keep the details and margins. The result image can be retained after reverting to the original color space. Our result illustrates the com- parison among result images and images enhanced by other methods, which obviously proves that the algorithm in our paper can obtain relatively better results in the ways of detail enhancement and color fidelity.