Jang-Ho Choi — accepted AI-conference papers

2026

Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection

Dahye Kim, Jaehyun Choi, Hyun Seok Seong, Seongho Kim, Donghun Lee, Sungwon Yi +1

ICML 2026poster

While existing AI-generated image detectors report high performance, we identify that this is largely driven by a critical *prediction asymmetry*: a bias toward the real class that severely limits sensitivity to generated content, especially under standard post-processing operations such as compress…

Cited by 0 Source ↗Scholar ↗

2022

Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift

Taesung Kim, Jinhee Kim, Yunwon Tae, Cheonbok Park, Jang-Ho Choi, Jaegul Choo

ICLR 2022poster

Statistical properties such as mean and variance often change over time in time series, i.e., time-series data suffer from a distribution shift problem. This change in temporal distribution is one of the main challenges that prevent accurate time-series forecasting. To address this issue, we propose…

Cited by 667 Source ↗PDF ↗code ↗Scholar ↗