Selected work

Representative Papers

Approximate full-conformal multi-task regression with reproducing kernels

Jul 01, 2026

This work addresses the challenge of constructing fully conformal prediction regions in multi-task regression, which are typically intractable due to their reliance on an infinite ensemble of predictors. The authors propose a computationally feasible approximation within a vector-valued reproducing kernel Hilbert space, providing theoretical guarantees of achieving the desired coverage level under both known and estimated covariance matrices. In the case of known covariance, they derive an upper bound on the volume of the prediction region and establish its tightness. Empirical evaluations on synthetic data demonstrate that the proposed method substantially outperforms split conformal prediction, yielding significantly smaller prediction regions while maintaining accurate coverage.

0 citationsRead paper

Interpretable Computer Vision for Defect Detection in X-ray Tomography of Aerospace SiC/SiC Composites

May 19, 2026

This study addresses the lack of interpretability and decision traceability in deep learning models for detecting defects in aerospace-grade SiC/SiC composites using X-ray computed tomography (XCT). To this end, the authors propose p-ResNet-50, a framework that integrates a prototype layer into ResNet-50 to explicitly link classification outcomes to expert-defined semantic defect categories. Anchor and medoid regularization are introduced to mitigate prototype collapse, while UMAP-based latent space visualization enables clear identification of regions with high prediction uncertainty. Evaluated on approximately 12,000 XCT image patches, the method achieves an accuracy of 0.957 and a ROC-AUC of 0.994—matching the performance of black-box baselines—while simultaneously delivering auditable and human-interpretable decision rationales.

0 citationsRead paper

StreakMind: AI detection and analysis of satellite streaks in astronomical images with automated database integration

May 05, 2026

This work addresses the significant contamination of astronomical survey images by streaks from artificial satellites and space debris, which severely degrades data quality. The authors propose the first end-to-end automated framework for detecting and characterizing such streaks, introducing the novel application of the YOLO OBB model to astronomical streak detection. The pipeline integrates geometric refinement, cross-frame association, Gaussian-based confidence scoring, and cross-validation against orbital databases to enable fully automated processing—from image detection to structured archival. Evaluated on a test dataset, the system achieves 94% precision and 97% recall, demonstrating robust detection of faint streaks alongside high-fidelity geometric reconstruction and reliable satellite identification.

0 citationsRead paper

Approximate full conformal prediction in an RKHS

Jan 19, 2026

This work addresses the intractability of exact conformal prediction for real-valued outputs, which requires training infinitely many estimators and renders confidence regions computationally prohibitive. The authors propose a general framework to efficiently construct a tight approximation of the full conformal prediction region within a reproducing kernel Hilbert space (RKHS). By introducing a notion of “thickness” to quantify the deviation between the approximate and true conformal regions, and leveraging the smoothness of the loss and score functions, they establish approximation error bounds that depend explicitly on the regularity of the underlying function. This approach not only enables scalable computation of conformal confidence regions but also provides rigorous theoretical guarantees on the tightness of the approximation.

0 citationsRead paper

Reward-Preserving Attacks For Robust Reinforcement Learning

Jan 12, 2026arXiv.org

This work addresses the challenge of balancing attack strength in adversarial reinforcement learning: overly strong perturbations degrade nominal performance, while excessively weak ones fail to enhance robustness, and the optimal perturbation intensity varies dynamically across states. To this end, the paper proposes the α-reward-preserving attack, the first method to introduce a state-adaptive perturbation mechanism that enforces, in each state, a worst-case return at least an α-fraction below the nominal return through a state-dependent perturbation magnitude η. The approach calibrates attacks by combining gradient-based direction with an off-policy trained Q-function \( Q^\pi_\alpha((s,a), \eta) \) parameterized by a radius. Experiments demonstrate that the method consistently outperforms fixed- or random-radius baselines across various perturbation radii, achieving superior robustness without compromising nominal performance.

0 citationsRead paper

Recent publications

Latest Papers

Approximate full-conformal multi-task regression with reproducing kernels

Jul 01, 2026

This work addresses the challenge of constructing fully conformal prediction regions in multi-task regression, which are typically intractable due to their reliance on an infinite ensemble of predictors. The authors propose a computationally feasible approximation within a vector-valued reproducing kernel Hilbert space, providing theoretical guarantees of achieving the desired coverage level under both known and estimated covariance matrices. In the case of known covariance, they derive an upper bound on the volume of the prediction region and establish its tightness. Empirical evaluations on synthetic data demonstrate that the proposed method substantially outperforms split conformal prediction, yielding significantly smaller prediction regions while maintaining accurate coverage.

0 citationsRead paper

Interpretable Computer Vision for Defect Detection in X-ray Tomography of Aerospace SiC/SiC Composites

May 19, 2026

This study addresses the lack of interpretability and decision traceability in deep learning models for detecting defects in aerospace-grade SiC/SiC composites using X-ray computed tomography (XCT). To this end, the authors propose p-ResNet-50, a framework that integrates a prototype layer into ResNet-50 to explicitly link classification outcomes to expert-defined semantic defect categories. Anchor and medoid regularization are introduced to mitigate prototype collapse, while UMAP-based latent space visualization enables clear identification of regions with high prediction uncertainty. Evaluated on approximately 12,000 XCT image patches, the method achieves an accuracy of 0.957 and a ROC-AUC of 0.994—matching the performance of black-box baselines—while simultaneously delivering auditable and human-interpretable decision rationales.

0 citationsRead paper

StreakMind: AI detection and analysis of satellite streaks in astronomical images with automated database integration

May 05, 2026

This work addresses the significant contamination of astronomical survey images by streaks from artificial satellites and space debris, which severely degrades data quality. The authors propose the first end-to-end automated framework for detecting and characterizing such streaks, introducing the novel application of the YOLO OBB model to astronomical streak detection. The pipeline integrates geometric refinement, cross-frame association, Gaussian-based confidence scoring, and cross-validation against orbital databases to enable fully automated processing—from image detection to structured archival. Evaluated on a test dataset, the system achieves 94% precision and 97% recall, demonstrating robust detection of faint streaks alongside high-fidelity geometric reconstruction and reliable satellite identification.

0 citationsRead paper

Approximate full conformal prediction in an RKHS

Jan 19, 2026

This work addresses the intractability of exact conformal prediction for real-valued outputs, which requires training infinitely many estimators and renders confidence regions computationally prohibitive. The authors propose a general framework to efficiently construct a tight approximation of the full conformal prediction region within a reproducing kernel Hilbert space (RKHS). By introducing a notion of “thickness” to quantify the deviation between the approximate and true conformal regions, and leveraging the smoothness of the loss and score functions, they establish approximation error bounds that depend explicitly on the regularity of the underlying function. This approach not only enables scalable computation of conformal confidence regions but also provides rigorous theoretical guarantees on the tightness of the approximation.

0 citationsRead paper

Reward-Preserving Attacks For Robust Reinforcement Learning

Jan 12, 2026arXiv.org

This work addresses the challenge of balancing attack strength in adversarial reinforcement learning: overly strong perturbations degrade nominal performance, while excessively weak ones fail to enhance robustness, and the optimal perturbation intensity varies dynamically across states. To this end, the paper proposes the α-reward-preserving attack, the first method to introduce a state-adaptive perturbation mechanism that enforces, in each state, a worst-case return at least an α-fraction below the nominal return through a state-dependent perturbation magnitude η. The approach calibrates attacks by combining gradient-based direction with an off-policy trained Q-function \( Q^\pi_\alpha((s,a), \eta) \) parameterized by a radius. Experiments demonstrate that the method consistently outperforms fixed- or random-radius baselines across various perturbation radii, achieving superior robustness without compromising nominal performance.

0 citationsRead paper