arXiv subjects

Zhongzheng Xu

Publications and source records attributed to Zhongzheng Xu.

4 recordsLinked to original sources

arXiv2026

"Code Is Cheap. Show Me the Talk.": Lessons from Teaching and Managing AI Coding Tool Usage in a Visualization Course

Generative Artificial Intelligence (GenAI) coding tools are transforming visualization education. They can assist with implementation and design, but they can also let students bypass intended learning trajectories. In this paper, we share our retrospective experience managing and teaching AI use in an upper-level visualization course. We implemented prompt injections, asked oral checkout questions, and taught two AI coding labs. Prior to our coding labs, at least half of the students had already used AI tools in their assignments. In both AI coding labs, refinement accounted for about half of students' prompting logs, and explanation was almost absent. In the lab where AI coding was optional, 44 of 78 (56.4%) submissions preferred the scaffolded instructions over designing their own prompts. Students' final projects were more polished than in our previous offering, but also more visually homogeneous. Our reflections point to the need for clearer AI use boundaries and instruction on prompting, and for teaching students to question generic AI designs and adapt them to their data and story.

cs.HC↗

arXiv2026

Trace-Aware Workflows for Co-Creating Branded Content with Generative AI

Generative AI tools have lowered barriers to producing branded social media images and captions, yet small-business owners (SBOs) still struggle to create on-brand posts without access to professional designers or marketing consultants. Although these tools enable fast image generation from text prompts, aligning outputs with a brand's intended look and feel remains a demanding, iterative task. In this position paper, we explore how SBOs navigate iterative content creation and how AI-assisted systems can support SBOs' content creation workflow. We conducted a preliminary study with 12 SBOs who independently manage their businesses and social media presence, using a questionnaire to collect their branding practices, content workflows, and use of generative AI alongside conventional design tools. We identified three recurring challenges: (1) translating brand "feel" into effective prompts, (2) difficulty revisiting and comparing prior image generations, and (3) difficulty making sense of changes between iterations to steer refinement. Based on these findings, we present a prototype that scaffolds brand articulation, supports feedback-informed exploration, and maintains a traceboard of branching image iterations. Our work illustrates how traces of the iterative process can serve as workflow support that helps SBOs keep track of explorations, make sense of changes, and refine content.

cs.HC↗

arXiv2024

Exploring the Capability of LLMs in Performing Low-Level Visual Analytic Tasks on SVG Data Visualizations

Data visualizations help extract insights from datasets, but reaching these insights requires decomposing high level goals into low-level analytic tasks that can be complex due to varying degrees of data literacy and visualization experience. Recent advancements in large language models (LLMs) have shown promise for lowering barriers for users to achieve tasks such as writing code and may likewise facilitate visualization insight. Scalable Vector Graphics (SVG), a text-based image format common in data visualizations, matches well with the text sequence processing of transformer-based LLMs. In this paper, we explore the capability of LLMs to perform 10 low-level visual analytic tasks defined by Amar, Eagan, and Stasko directly on SVG-based visualizations. Using zero-shot prompts, we instruct the models to provide responses or modify the SVG code based on given visualizations. Our findings demonstrate that LLMs can effectively modify existing SVG visualizations for some tasks like Cluster but perform poorly on tasks requiring mathematical operations like Compute Derived Value. We also discovered that LLM performance can vary based on factors such as the number of data points, the presence of value labels, and the chart type. Our findings contribute to gauging the general capabilities of LLMs and highlight the need for further exploration and development to fully harness their potential in supporting visual analytic tasks.

cs.HC↗

arXiv2023

Let's Get Vysical: Perceptual Accuracy In Visual and Tactile Encodings

In this paper, we explore the effectiveness of tactile data encodings using swell paper in comparison to visual encodings displayed with SVGs for data perception tasks. By replicating and adapting Cleveland and McGill's graphical perception study for the tactile modality, we establish a novel tactile encoding hierarchy. In a study with 12 university students, we found that participants perceived visual encodings more accurately when comparing values, judging their ratios with lower cognitive load, and better self-evaluated performance than tactile encodings. However, tactile encodings differed from their visual counterparts in terms of how accurately values could be decoded from them. This suggests that data physicalizations will require different design guidance than that developed for visual encodings. By providing empirical evidence for the perceptual accuracy of tactile encodings, our work contributes to foundational research on forms of data representation that prioritize tactile perception such as tactile graphics.

cs.HC↗