6 papers · 1 filter
EvoMaestro: Toward Interpretable and Steerable LLM-Driven Program Evolution
Feng Liang, Sizhe Cheng, Yikai Li +3
Recent program evolution systems use large language models (LLMs) to generate and iteratively improve populations of programs, producing striking advances in mathematics, algorithm…
VizPilot: Automated Onboarding for SVG-based Composite Visualizations using Multimodal LLMs
Nishaanthini Gnanavel, Yong Wang
Composite visualizations integrate multiple visualizations to represent complex datasets effectively, but their intrinsic composite designs often impose a high initial cognitive lo…
ManiScope: LLM-Assisted Visual Analytics of Cryptocurrency Manipulation Risk
Xiaolin Wen, Feng Liang, Yuanye Ma +5
Cryptocurrency markets are vulnerable to trade-based manipulation, such as wash trading, which can distort price signals and mislead investors. Prior research has mainly focused on…
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…