cv

Ph.D.

Georgia Institute of Technology

Computer Science

• Data Vis Principles
• Inform Visualization
• Data & Visual Analytic
• Human-Computer Interact
• Computer Vision
• Psychological Statistics

B.Eng.

Shanghai Jiao Tong University

Electrical and Computer Engineering

• Calculus
• Linear Algebra
• Probabilistic Methods in Engineering
• Discrete Mathematics
• Programming & Elementary Data Structures
• Data Structures & Algorithms
• Intro to Data Science
• Computer Organization
• Signals & Systems
• Circuits
• Logic Design
• Software Engineering
• Intro to Artificial Intelligence
• Machine Learning

Embedded Software Engineer Intern

Bosch China

Deep Learning-based Gesture Recognition Algorithm Development

• Developed gesture recognition algorithms for Human-Vehicle Interaction using DNN.
• Applied the attention network to the neural network for dynamic gesture classification.
• Achieved 90% accuracy for 16 static gestures and 9 dynamic gestures on webcam with 720p@30fps.

Interactive Visualization Recommendation with Hier-SUCB

International World Wide Web Conference 2025 (WWW 25')

Accepted by International World Wide Web Conference 2025

VisChatter: Enhance Synchronous Collaboration on Visualization Dashboard through Visual Annotations

Annual Meeting of the Cognitive Science Society 2025 (CogSci 25')

Presented at the Annual Meeting of the Cognitive Science Society 2025

Perceptual Benefits of Animation are Task-Dependent: Effects of Staging and Tracing in Dynamic Displays

IEEE Visualization Conference 2024 (VIS 24')

Accepted by IEEE Visualization Conference 2024

Hierarchical Conversational Preference Elicitation with Bandit Feedback

Conference on Information and Knowledge Management 2022 (CIKM 22')

Accepted by Conference on Information and Knowledge Management 2022

VisChatter – Visual Annotations for Collaborative Analytics

• Designed and implemented an interactive visualization dashboard with real-time annotation to enable synchronous collaborative analytics.
• Integrated speech recognition API, LLM-based keyword extraction, and custom annotation APIs for seamless multimodal input.
• Conducted controlled A/B testing against baseline tools, measuring user engagement and task efficiency improvements, and collected qualitative feedback via in-person studies.

Interactive Visualization Recommendation with Hier-SUCB

• Developed a hierarchical bandit-based recommendation model to personalize visualization suggestions from user interaction histories.
• Incorporated a bias term to model individual preferences and optimize recommendation relevance.
• Performed A/B testing on the Plot.ly dataset, validating performance through an online user study.

Hierarchical Conversational Preference Elicitation with Bandit Feedback

• Proposed and implemented a multi-armed bandit algorithm for preference elicitation in hierarchical item spaces.
• Ran large-scale simulations demonstrating performance gains over baseline algorithms.
• Conducted online user study on the Yelp dataset to validate real-world applicability.