7 papers
Beyond Counting Blessings: Tracing the Evolution of Gratitude Practices and Technology Needs
Joy Qiuyue Zhong, Jeongah Lee, Drishti Goel +4
Gratitude technologies support well-being by prompting reflection on what people appreciate. But gratitude does not serve the same purpose in every circumstance: as life situations…
E3Sense: Head-Confined Multimodal Sensing of Learner Engagement
Sidharth Anupkrishnan, Itir Sayar, Jeongah Lee +5
Engagement-aware learning systems could provide hints or adjust pacing when learners struggle. Prior engagement sensing work distributes sensors across or outside the body rather t…
Can LLMs identify and repair ruptures? Comparison between clinician practices and LLM behaviors
Jeongah Lee, Joy Qiuyue Zhong, Drishti Goel +4
Ruptures represent common albeit critical moments in interaction where relational alignment breaks down, making them essential for evaluating AI where trust and engagement matter m…
Cohort-based Semantic Labeling: AI-Enabled Recovery of Visualization Semantics from Deployed SVGs
Jeongah Lee, Hima Varshini Surisetty, Durga Nirmaleswaran +4
Many web-based visualizations are deployed as Scalable Vector Graphics (SVG), a format that faithfully preserves visual appearance but typically omits the higher-level semantic str…
RubRIX: Rubric-Driven Risk Mitigation in Caregiver-AI Interactions
Drishti Goel, Jeongah Lee, Qiuyue Joy Zhong +5
Caregivers seeking AI-mediated support express complex needs---information-seeking, emotional validation, and distress cues---that warrant careful evaluation of response safety and…
SVG Decomposition for Enhancing Large Multimodal Models Visualization Comprehension: A Study with Floor Plans
Jeongah Lee, Ali Sarvghad
Large multimodal models (LMMs) are increasingly capable of interpreting visualizations, yet they continue to struggle with spatial reasoning. One proposed strategy is decomposition…
From Text to Visuals: Using LLMs to Generate Math Diagrams with Vector Graphics
Jaewook Lee, Jeongah Lee, Wanyong Feng +1
Advances in large language models (LLMs) offer new possibilities for enhancing math education by automating support for both teachers and students. While prior work has focused on…