7 papers
Beyond Averages: Evaluating LLMs on Human Survey Replication at the Distributional Level
Jeonghyeon Moon, Jiwon Kim, Yeheum Lah +2
LLMs are increasingly used to simulate human survey responses, but prior work has mainly evaluated replication using mean-level or aggregate agreement, offering limited insight int…
Efficient Traffic Prediction at Scale: A Systematic Study of STGCN Architectural Depth
Soban Nasir Lone, Mohamed Abouelela, Taeyoung Yu +2
Spatio-temporal graph neural networks (STGNNs) have become the dominant approach for traffic prediction, yet their computational requirements pose challenges for practical deployme…
MedROI: Codec-Agnostic Region of Interest-Centric Compression for Medical Images
Jiwon Kim, Ikbeom Jang
Medical imaging archives are growing rapidly in both size and resolution, making efficient compression increasingly important for storage and data transfer. Most existing codecs co…
Automated Traffic Incident Response Plans using Generative Artificial Intelligence: Part 1 -- Building the Incident Response Benchmark
Artur Grigorev, Khaled Saleh, Jiwon Kim +1
Traffic incidents remain a critical public safety concern worldwide, with Australia recording 1,300 road fatalities in 2024, which is the highest toll in 12 years. Similarly, the U…
Understanding everyday public transit travel habits: a measurement framework for the peakedness of departure time distributions
Jiwon Kim, Jonathan Corcoran
Persuasive scholarship presents how individual daily travel habits implicate congestion, environmental pollution, and the travel experience. However, the empirical characteristics…
A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research
Seongjin Choi, Zhixiong Jin, Seung Woo Ham +2
Deep Generative Models (DGMs) have rapidly advanced in recent years, becoming essential tools in various fields due to their ability to learn complex data distributions and generat…