Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Unggi Lee

Unggi Lee

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×1AI×1

Frequent co-authors

Yeil Jeong1×
Youngjin Yoo1×
Seobin Sohn1×
Hyejin Han1×
Jinseo Lee1×
Scott Howard1×

Research Timeline

2026
BuddyBench: A Privacy-Constrained Multi-Task Benchmark for Pediatric Social-Communication Personalization

BuddyBench introduces a novel, privacy-constrained multi-task benchmark that integrates longitudinal learning trajectories, standardized clinical assessments, and randomized trial data to advance pediatric social-communication personalization.

TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation

The paper introduces TeachObs, a comprehensive, human-validated benchmark for multimodal teaching observation, and evaluates frontier LLMs, finding that no single model consistently outperforms others and that expert judgment remains crucial for accurate analysis.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentMay 29, 2026

TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation

Yeil Jeong, Youngjin Yoo, Seobin Sohn, Hyejin Han +3 more

The paper introduces TeachObs, a comprehensive, human-validated benchmark for multimodal teaching observation, and evaluates frontier LLMs, finding that no single model consistently outperforms others…

View →
cs.AIRecentMay 27, 2026

BuddyBench: A Privacy-Constrained Multi-Task Benchmark for Pediatric Social-Communication Personalization

Jeyeon Eo, Joo Young Kim, Ran Ju, Minyoung Jung +1 more

BuddyBench introduces a novel, privacy-constrained multi-task benchmark that integrates longitudinal learning trajectories, standardized clinical assessments, and randomized trial data to advance pedi…

View →