8 papers
VizPilot: Automated Onboarding for SVG-based Composite Visualizations using Multimodal LLMs
Nishaanthini Gnanavel, Yong Wang
VizPilot is a browser extension that automatically creates interactive onboarding guides for SVG-based composite visualizations by analyzing their structure with multimodal large l…
ManiScope: LLM-Assisted Visual Analytics of Cryptocurrency Manipulation Risk
Xiaolin Wen, Feng Liang, Yuanye Ma +5
ManiScope is a visual analytics system that uses a large language model as a co‑analyst to help users explore and assess trade‑based manipulation risks in cryptocurrency markets.
Vibe Coding for Visualization Implementation: An Empirical Study of Practices and Challenges
Zhengyu Sun, Xiaolin Wen, Fengjie Wang +4
Data visualization is essential for data analysis and communication, yet creating expressive visualizations remains labor-intensive. Recent AI-driven ``vibe coding'' tools enable u…
When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors
Shiwei Chen, Niruthikka Sritharan, Xiaolin Wen +3
Current Large Language Models (LLMs), especially Large Reasoning Models, can generate Chain-of-Thought (CoT) reasoning traces to illustrate how they produce final outputs, thereby…
Human in the Loop for Fuzz Testing: Literature Review and the Road Ahead
Jiongchi Yu, Xiaolin Wen, Sizhe Cheng +3
Fuzz testing is one of the most effective techniques for detecting bugs and vulnerabilities in software. However, as the basis of fuzz testing, automated heuristics often fail to u…
Envisage: Towards Expressive Visual Graph Querying
Xiaolin Wen, Qishuang Fu, Shuangyue Han +3
Graph querying is the process of retrieving information from graph data using specialized languages (e.g., Cypher), often requiring programming expertise. Visual Graph Querying (VG…