Selected work

Representative Papers

Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions

May 21, 2026

This work addresses the challenge of simultaneously achieving low reconstruction error and faithful preservation of critical local features—such as derivative peaks—in real-world time series corrupted by a mixture of Gaussian noise and out-of-distribution impulsive anomalies. To this end, the authors propose a training-free recovery framework that uniquely integrates two-dimensional (time–amplitude) kernel density estimation with density-truncated robust expectation to suppress anomaly influence, complemented by an adaptively terminated exponential cascade mechanism for fine-grained signal restoration. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method significantly outperforms conventional filters and learning-based baselines in terms of waveform fidelity, derivative preservation, downstream classification accuracy, and computational efficiency, thereby unifying robustness with accurate retention of local structural characteristics.

0 citationsRead paper

ContextGuard-LVLM: Enhancing News Veracity through Fine-grained Cross-modal Contextual Consistency Verification

Aug 08, 2025

This study addresses the challenge of verifying fine-grained cross-modal consistency—specifically in narrative logic, affective valence, and scene-event alignment—between visual and textual elements in digital news. To this end, we propose the first Fine-grained Cross-modal Contextual Consistency (FCCC) detection framework. Methodologically, it employs a multi-stage contextual reasoning mechanism and introduces three annotation dimensions: affective polarity, visual narrative theme, and event-logical coherence, formalized via a novel CTXT entity type. Leveraging vision-language foundation models, the framework integrates reinforcement learning and adversarial training to enhance sensitivity to latent inconsistencies. Experimental results demonstrate that our approach significantly outperforms zero-shot baselines across multiple augmented datasets. It achieves breakthroughs in logical reasoning capability, robustness against input perturbations, and alignment with human expert judgments—establishing a new state of the art in fine-grained multimodal consistency assessment.

0 citationsRead paper

Recent publications

Latest Papers

Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions

May 21, 2026

This work addresses the challenge of simultaneously achieving low reconstruction error and faithful preservation of critical local features—such as derivative peaks—in real-world time series corrupted by a mixture of Gaussian noise and out-of-distribution impulsive anomalies. To this end, the authors propose a training-free recovery framework that uniquely integrates two-dimensional (time–amplitude) kernel density estimation with density-truncated robust expectation to suppress anomaly influence, complemented by an adaptively terminated exponential cascade mechanism for fine-grained signal restoration. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method significantly outperforms conventional filters and learning-based baselines in terms of waveform fidelity, derivative preservation, downstream classification accuracy, and computational efficiency, thereby unifying robustness with accurate retention of local structural characteristics.

0 citationsRead paper

ContextGuard-LVLM: Enhancing News Veracity through Fine-grained Cross-modal Contextual Consistency Verification

Aug 08, 2025

This study addresses the challenge of verifying fine-grained cross-modal consistency—specifically in narrative logic, affective valence, and scene-event alignment—between visual and textual elements in digital news. To this end, we propose the first Fine-grained Cross-modal Contextual Consistency (FCCC) detection framework. Methodologically, it employs a multi-stage contextual reasoning mechanism and introduces three annotation dimensions: affective polarity, visual narrative theme, and event-logical coherence, formalized via a novel CTXT entity type. Leveraging vision-language foundation models, the framework integrates reinforcement learning and adversarial training to enhance sensitivity to latent inconsistencies. Experimental results demonstrate that our approach significantly outperforms zero-shot baselines across multiple augmented datasets. It achieves breakthroughs in logical reasoning capability, robustness against input perturbations, and alignment with human expert judgments—establishing a new state of the art in fine-grained multimodal consistency assessment.

0 citationsRead paper