7 papers
Natural State-Prediction Accuracy can Hide Weak Controlled Responsiveness in VLA Readouts
Hyungjoon Kim, Wonbin Son, Mi Young Lee +2
Accurately decoding object states from the internal representations of vision-language-action (VLA) models does not establish that the predictions respond faithfully to changes in…
When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals
Wonbin Son, Gyumun Choi, Junil Seo +3
Answering what-if queries about a scene with a VLM usually means injecting the assumption as text or repainting the scene with a generative model. We instead move the edit to the r…
PaGNet: A Panel-Aware GBDT--Neural Network for Multi-Target Corporate Tax Avoidance Proxy Forecasting
Wonho Song, Hyungjoon Kim
Forecasting corporate tax avoidance proxies from firm--year panel data is challenging because predictive signals are distributed across short firm histories and related targets, wh…
A Comprehensive Bayesian Approach to Entity Resolution for Data with Multiple Truths
Hyungjoon Kim, Andee Kaplan, Matthew D. Koslovsky
In many applications, from government to ecology, integrating data from diverse and noisy sources is critical for downstream inference. However, a unique identifier to link records…
KRAFT: A Transaction-Level Dataset for Korean Apartment Sales Integrated with Contextual Indicators
Sejin Myung, Hyungjoon Kim
Apartment transaction records are useful for studying housing markets, household finance, regional economics, and macro-financial transmission, but transaction data are often distr…
MIRCaps: A Large-Scale Mixed-Domain Dataset with Image-Level and Region-Level Captions for Fine-Grained Vision-Language Learning
Arlindo Luciano Tulumba Roberto, Hyungjoon Kim
Despite recent progress in Vision-Language Models (VLMs), mixed-domain image-caption datasets for both general-purpose and CCTV-based video surveillance systems remain limited. To…
KoTaP: A Panel Dataset for Corporate Tax Avoidance, Performance, and Governance in Korea
Hyungjong Na, Wonho Song, Seungyong Han +3
This study introduces the Korean Tax Avoidance Panel (KoTaP), a long-term panel dataset of non-financial firms listed on KOSPI and KOSDAQ between 2011 and 2024. After excluding fin…