3 papers
cs.AI2026
GRAIL: From Saliency to Semantics in Time-Series Explanation
Enver Menadjiev, Yiqiu Shen, Jaesik Choi +1
Explaining a time-series model requires both locating the evidence and extracting meaningful knowledge from it. Yet a single timestep is not a semantic unit: the meaningful pattern…
cs.LG2026
DistMatch: Adaptive Binning via Distribution Matching for Robust Sequential Conformal Prediction
Enver Menadjiev, Jihyeon Seong, Jisu Yeo +1
Sequential conformal prediction (CP) provides valid uncertainty quantification under the assumption of residual exchangeability. However, this assumption is often violated in real-…
cs.LG2025
PnPXAI: A Universal XAI Framework Providing Automatic Explanations Across Diverse Modalities and Models
Seongun Kim, Sol A Kim, Geonhyeong Kim +5
Recently, post hoc explanation methods have emerged to enhance model transparency by attributing model outputs to input features. However, these methods face challenges due to thei…