Yuheng Zhao

Yuheng Zhao

Auto-generated profile, based on publicly available information

Yuheng Zhao

Fudan University, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
23 March 2022 in Visual Informatics
Verified
Journal Article
Open access
YZYuheng Zhao
Yuheng Zhao
JJJinjing Jiang
Jinjing Jiang
YCYi Chen
Yi Chen
RLRichen Liu
Richen Liu
YYYalong Yang
Yalong Yang
SCSiming Chen
Siming Chen

4 March 2024 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YZYuheng Zhao
Yuheng Zhao
YZYixing Zhang
Yixing Zhang
YZYu Zhang
Yu Zhang
XZXinyi Zhao
Xinyi Zhao
JWJunjie Wang
Junjie Wang
SCSiming Chen
Siming Chen
Visual analytics supports data analysis tasks within complex domain problems. However, due to the richness of data types, visual designs, and interaction designs, users need to recall and process a significant amount of information when they visually analyze data. These challenges emphasize the need for more intelligent visual analytics methods. Large language models have demonstrated the ability to interpret various forms of textual data, offering the potential to facilitate intelligent support for visual analytics. We propose LEVA, a framework that uses large language models to enhance users' VA workflows at multiple stages: onboarding, exploration, and summarization. To support onboarding, we use large language models to interpret visualization designs and view relationships based on system specifications. For exploration, we use large language models to recommend insights based on the analysis of system status and data to facilitate mixed-initiative exploration. For summarization, we present a selective reporting strategy to retrace analysis history through a stream visualization and generate insight reports with the help of large language models. We demonstrate how LEVA can be integrated into existing visual analytics systems. Two usage scenarios and a user study suggest that LEVA effectively aids users in conducting visual analytics.

14 November 2024 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YZYuheng Zhao
Yuheng Zhao
JWJunjie Wang
Junjie Wang
LXLinbing Xiang
Linbing Xiang
XZXiaowen Zhang
Xiaowen Zhang
ZGZifei Guo
Zifei Guo
SCSiming Chen
Siming Chen
Visual analytics requires analysts to constantly plan and execute analysis tasks based on observations and generate visualizations and support analysis for gaining insights from data. Completing this process requires significant effort, emphasizing the necessity for a more intelligent and lightweight visual analytics process. Large language model agents have shown capabilities in logic inference and code generation, offering the potential to lower development costs and enhance the versatility of visual analytics. We propose LightVA, a lightweight visual analytics framework that completes task proposal, data modeling and interactive visual exploration with human-agent collaboration. Our method is grounded on the relationships among the goal, task, data, visualization, and insight. Specifically, we introduce an LLM-agent-based task-planning and execution method that supports task planning and execution, employing a recursive process involving a planner, executor, and controller, dynamically accommodating task complexity. The planner is responsible for task decomposition, the executor handles task execution, including visualization generation and data analysis, and the controller orchestrates the executor and planner. Based on the LightVA framework, we develop a system consisting of a task flow diagram and interactive visualization panel, which makes the workflow more controllable and transparent. We examine the effectiveness of our method through a usage scenario and an expert study.

28 February 2023 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
ZSZekai Shao
Zekai Shao
SSShuran Sun
Shuran Sun
YZYuheng Zhao
Yuheng Zhao
SWSiyuan Wang
Siyuan Wang
ZWZhongyu Wei
Zhongyu Wei
SCSiming Chen
Siming Chen
Open-domain question answering (OpenQA) is an essential but challenging task in natural language processing that aims to answer questions in natural language formats on the basis of large-scale unstructured passages. Recent research has taken the performance of benchmark datasets to new heights, especially when these datasets are combined with techniques for machine reading comprehension based on Transformer models. However, as identified through our ongoing collaboration with domain experts and our review of literature, three key challenges limit their further improvement: (i) complex data with multiple long texts, (ii) complex model architecture with multiple modules, and (iii) semantically complex decision process. In this paper, we present VEQA, a visual analytics system that helps experts understand the decision reasons of OpenQA and provides insights into model improvement. The system summarizes the data flow within and between modules in the OpenQA model as the decision process takes place at the summary, instance and candidate levels. Specifically, it guides users through a summary visualization of dataset and module response to explore individual instances with a ranking visualization that incorporates context. Furthermore, VEQA supports fine-grained exploration of the decision flow within a single module through a comparative tree visualization. We demonstrate the effectiveness of VEQA in promoting interpretability and providing insights into model enhancement through a case study and expert evaluation.

24 October 2023 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YZYu Zhang
Yu Zhang
RJRuike Jiang
Ruike Jiang
LXLiwenhan Xie
Liwenhan Xie
YZYuheng Zhao
Yuheng Zhao
CLCan Liu
Can Liu
XYXiaoru Yuan
Xiaoru Yuan
With the increasing adoption of digitization, more and more historical visualizations created hundreds of years ago are accessible in digital libraries online. It provides a unique opportunity for visualization and history research. Meanwhile, there is no large-scale digital collection dedicated to historical visualizations. The visualizations are scattered in various collections, which hinders retrieval. In this study, we curate the first large-scale dataset dedicated to historical visualizations. Our dataset comprises 13K historical visualization images with corresponding processed metadata from seven digital libraries. In curating the dataset, we propose a workflow to scrape and process heterogeneous metadata. We develop a semi-automatic labeling approach to distinguish visualizations from other artifacts. Our dataset can be accessed with OldVisOnline, a system we have built to browse and label historical visualizations. We discuss our vision of usage scenarios and research opportunities with our dataset, such as textual criticism for historical visualizations. Drawing upon our experience, we summarize recommendations for future efforts to improve our dataset.

15 December 2025 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YZYuheng Zhao
Yuheng Zhao
JLJingqiu Liang
Jingqiu Liang
LFLiwen Fan
Liwen Fan
LGLin Gao
Lin Gao
YZYu Zhang
Yu Zhang
SCSiming Chen
Siming Chen
Visual analytics (VA) is typically applied to complex data, thus requiring complex tools. While visual analytics empowers analysts in data analysis, analysts may get lost in the complexity occasionally. This highlights the need for intelligent assistance mechanisms. However, even the latest LLM-assisted VA systems only provide help when explicitly requested by the user, making them insufficiently intelligent to offer suggestions when analysts need them the most. We propose a ProactiveVA framework in which LLM-powered UI agent monitors user interactions and delivers context-aware assistance proactively. To design effective proactive assistance, we first conducted a formative study analyzing help-seeking behaviors in user interaction logs, identifying when users need proactive help, what assistance they require, and how the agent should intervene. Based on this analysis, we distilled key design requirements in terms of intent recognition, solution generation, interpretability and controllability. Guided by these requirements, we develop a three-stage UI agent pipeline including perception, reasoning, and acting. The agent autonomously perceives users' needs from VA interaction logs, providing tailored suggestions and intuitive guidance through interactive exploration of the system. We implemented the framework in two representative types of VA systems, demonstrating its generalizability, and evaluated the effectiveness through an algorithm evaluation, case and expert study and a user study. We also discuss current design trade-offs of proactive VA and areas for further exploration.