Selected work

Representative Papers

Knowledge-guided Pattern Discovery via Coupled Tensor Factorizations

Aug 13, 2026

This work addresses the limitation of traditional tensor decomposition methods in incorporating prior knowledge from computational models when analyzing high-dimensional multi-way data, such as metabolomics datasets, which hinders the discovery of interpretable patterns. The authors propose a knowledge-guided coupled tensor decomposition framework that, for the first time, jointly analyzes real observational data and simulated data generated by computational models under linear coupling constraints. This approach enhances both robustness and interpretability of extracted patterns in noisy settings and successfully identifies latent inconsistencies between model predictions and empirical observations in real metabolomics data. The results demonstrate the method’s effectiveness and novelty in seamlessly integrating domain-specific prior knowledge with data-driven analysis.

0 citationsRead paper

Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology

Aug 13, 2026

Traditional clinical prediction models oversimplify postoperative outcomes as static mappings, neglecting the impact of asynchronous interventions and dynamic physiological changes during recovery. This work proposes the first intervention-aware clinical world model that formulates postoperative recovery as a temporal process driven by asynchronous clinical events. By encoding a 3D latent state that integrates baseline imaging, surgical context, static covariates, and peri-event physiological signals, the model enables dynamic state evolution over time. It supports multi-temporal risk queries and retrospective input editing, and can predict scar burden without requiring follow-up MRI. Evaluated on the DECAAF-II dataset, the model achieves an AUROC of 0.756 and AUPRC of 0.777 for predicting atrial fibrillation recurrence at 90 days post-ablation, with a mean absolute error of 2.971 percentage points in scar extent prediction.

0 citationsRead paper

Search-Based Generation of Undetected Quantum Circuit Mutants

Aug 10, 2026

This work addresses the limitations of existing quantum mutation analysis tools, which rely on fixed gate-level mutations that produce easily detectable mutants and thus inadequately evaluate test suite quality. To overcome this, the authors propose QUMUG, a novel approach that integrates search-based optimization with parameterized quantum gates. By employing a genetic algorithm to automatically tune gate parameters, QUMUG generates challenging, non-equivalent quantum circuit mutants capable of evading detection by current test suites. Experimental results across 30 quantum programs demonstrate that QUMUG’s mutants are, on average, three times harder to detect than those from existing tools, yielding 494 undetected mutants per program with a success rate of 99.67% and a non-equivalence ratio of 94.3%. Furthermore, these mutants prompted a fivefold expansion of test suites, substantially enhancing the effectiveness of quantum program testing.

0 citationsRead paper

Delta Debugging for Cyber-Physical Systems with Flaky Test Executions

Jul 28, 2026

This study addresses the challenge of reproducing failures in cyber-physical system (CPS) simulation testing, where non-deterministic behaviors often hinder consistent fault manifestation. To tackle this issue, the work extends delta debugging to stochastic CPS scenarios for the first time, introducing three novel delta debugging algorithms tailored for randomized environments. The proposed approach integrates statistical failure analysis, repeated execution, and environment-aware input minimization to identify a minimal triggering input while preserving fault semantics. Empirical evaluation on case studies involving elevator scheduling and autonomous mobile robots demonstrates that the method significantly enhances the stability of failure reproduction and substantially reduces debugging time, effectively mitigating execution flakiness inherent in such systems.

0 citationsRead paper

Latent PDE mapping for efficient physics-informed learning across geometries with limited data

Jul 24, 2026

This work addresses the poor generalization of existing physics-informed machine learning methods to unseen geometries under data-scarce conditions. The authors propose a latent-space PDE mapping approach that leverages deformation gradients to pull back geometry-dependent PDE residuals and boundary conditions onto a predefined reference geometry, enabling efficient cross-geometry learning. The method introduces, for the first time, an automatic shape-gradient computation mechanism that preserves geometric consistency and integrates physics-informed neural networks (PINNs) with deep operator networks (DeepONets) to construct the latent PDE map. Using only 15 geometric samples from a specific family, the approach reduces the average relative L² error by a factor of 4–6 compared to baseline methods, achieves low training overhead, and incurs negligible additional cost during inference.

0 citationsRead paper

Recent publications

Latest Papers

Knowledge-guided Pattern Discovery via Coupled Tensor Factorizations

Aug 13, 2026

This work addresses the limitation of traditional tensor decomposition methods in incorporating prior knowledge from computational models when analyzing high-dimensional multi-way data, such as metabolomics datasets, which hinders the discovery of interpretable patterns. The authors propose a knowledge-guided coupled tensor decomposition framework that, for the first time, jointly analyzes real observational data and simulated data generated by computational models under linear coupling constraints. This approach enhances both robustness and interpretability of extracted patterns in noisy settings and successfully identifies latent inconsistencies between model predictions and empirical observations in real metabolomics data. The results demonstrate the method’s effectiveness and novelty in seamlessly integrating domain-specific prior knowledge with data-driven analysis.

0 citationsRead paper

Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology

Aug 13, 2026

Traditional clinical prediction models oversimplify postoperative outcomes as static mappings, neglecting the impact of asynchronous interventions and dynamic physiological changes during recovery. This work proposes the first intervention-aware clinical world model that formulates postoperative recovery as a temporal process driven by asynchronous clinical events. By encoding a 3D latent state that integrates baseline imaging, surgical context, static covariates, and peri-event physiological signals, the model enables dynamic state evolution over time. It supports multi-temporal risk queries and retrospective input editing, and can predict scar burden without requiring follow-up MRI. Evaluated on the DECAAF-II dataset, the model achieves an AUROC of 0.756 and AUPRC of 0.777 for predicting atrial fibrillation recurrence at 90 days post-ablation, with a mean absolute error of 2.971 percentage points in scar extent prediction.

0 citationsRead paper

Search-Based Generation of Undetected Quantum Circuit Mutants

Aug 10, 2026

This work addresses the limitations of existing quantum mutation analysis tools, which rely on fixed gate-level mutations that produce easily detectable mutants and thus inadequately evaluate test suite quality. To overcome this, the authors propose QUMUG, a novel approach that integrates search-based optimization with parameterized quantum gates. By employing a genetic algorithm to automatically tune gate parameters, QUMUG generates challenging, non-equivalent quantum circuit mutants capable of evading detection by current test suites. Experimental results across 30 quantum programs demonstrate that QUMUG’s mutants are, on average, three times harder to detect than those from existing tools, yielding 494 undetected mutants per program with a success rate of 99.67% and a non-equivalence ratio of 94.3%. Furthermore, these mutants prompted a fivefold expansion of test suites, substantially enhancing the effectiveness of quantum program testing.

0 citationsRead paper

Delta Debugging for Cyber-Physical Systems with Flaky Test Executions

Jul 28, 2026

This study addresses the challenge of reproducing failures in cyber-physical system (CPS) simulation testing, where non-deterministic behaviors often hinder consistent fault manifestation. To tackle this issue, the work extends delta debugging to stochastic CPS scenarios for the first time, introducing three novel delta debugging algorithms tailored for randomized environments. The proposed approach integrates statistical failure analysis, repeated execution, and environment-aware input minimization to identify a minimal triggering input while preserving fault semantics. Empirical evaluation on case studies involving elevator scheduling and autonomous mobile robots demonstrates that the method significantly enhances the stability of failure reproduction and substantially reduces debugging time, effectively mitigating execution flakiness inherent in such systems.

0 citationsRead paper

Latent PDE mapping for efficient physics-informed learning across geometries with limited data

Jul 24, 2026

This work addresses the poor generalization of existing physics-informed machine learning methods to unseen geometries under data-scarce conditions. The authors propose a latent-space PDE mapping approach that leverages deformation gradients to pull back geometry-dependent PDE residuals and boundary conditions onto a predefined reference geometry, enabling efficient cross-geometry learning. The method introduces, for the first time, an automatic shape-gradient computation mechanism that preserves geometric consistency and integrates physics-informed neural networks (PINNs) with deep operator networks (DeepONets) to construct the latent PDE map. Using only 15 geometric samples from a specific family, the approach reduces the average relative L² error by a factor of 4–6 compared to baseline methods, achieves low training overhead, and incurs negligible additional cost during inference.

0 citationsRead paper