From the 1 of 11 linked papers with an AI index.
11 papers
Revisiting Channel Effectiveness: A Multi-Dimensional Evaluation with Primitive Visual Stimuli
Soohyun Lee, Seokhyeon Park, Minsuk Chang +1
Established channel effectiveness rankings primarily assess magnitude estimation accuracy in complete chart contexts, often neglecting other perceptual tasks such as discriminabili…
TailVis: Expressive Chart Refinement Preserving Data-Binding Integrity
Yumin Song, Seokhyeon Park, Soohyun Lee +4
TailVis is a visualization authoring tool that lets users make fine-grained, expressive edits to static charts while keeping the link between data and visual elements intact, using…
Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy
Soohyun Lee, Jaeyoung Kim, Seokhyeon Park +5
Large Vision-Language Models (LVLMs) show strong visualization interpretation, yet it is unclear whether their responses reflect genuine reasoning over visual evidence or factual p…
InFerActive: Interactive Tree-Based Exploration of LLM Sampling for Safety Evaluation
Junhyeong Hwangbo, Soohyun Lee, Hyeon Jeon +4
Even LLMs that appear safe during evaluation can still produce harmful responses in deployment. Because stochastic sampling yields different responses to the same prompt, low-proba…
HookLens: Visual Analytics for Understanding React Hooks Structures
Suyeon Hwang, Minkyu Kweon, Jeongmin Rhee +5
Maintaining and refactoring React web applications is challenging, as React code often becomes complex due to its core API called Hooks. For example, Hooks often lead developers to…
Bridging Gulfs in UI Generation through Semantic Guidance
Seokhyeon Park, Soohyun Lee, Eugene Choi +4
While generative AI enables high-fidelity UI generation from text prompts, users struggle to articulate design intent and evaluate or refine results-creating gulfs of execution and…