3 papers
cs.LG2026
CondPSE: A Polynomial-Filtered Structural Encoder with Conditional Modulation for Graphs
Woohyun Lee, Hogun Park
Message-passing graph neural networks are bounded by the 1-WL test and can miss topological structure that distinguishes non-isomorphic graphs. Positional and structural encodings…
cs.LG2026
Self-supervised Adversarial Purification for Graph Neural Networks
Woohyun Lee, Hogun Park
Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial…
cs.CV2026
JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QA
Hyunju Kang, Woohyun Lee, Jaewon Kim +1
Industrial anomaly detection has been significantly advanced by Large Multimodal Models (LMMs), enabling diverse human instructions beyond detection, particularly through visually…