Selected work

Representative Papers

RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation

Aug 12, 2026

This work addresses the longstanding challenge in real-time speech enhancement of simultaneously achieving high audio quality and low latency. To this end, it introduces Mamba—a state space model—into this domain for the first time, proposing a fully causal architecture built upon causal time-frequency Mamba blocks. To mitigate computational overhead, the authors devise a progressive knowledge distillation strategy that jointly transfers both spectral outputs and intermediate representations from an 8-layer teacher model to a single-layer student model. Evaluated on the Voicebank-DEMAND dataset, the distilled student model achieves a PESQ score of 3.18—improved from 3.06—with only 25 ms of latency and a 2.75× speedup in inference, significantly outperforming current state-of-the-art approaches.

0 citationsRead paper

DSXFormer: Dual-Pooling Spectral Squeeze-Expansion and Dynamic Context Attention Transformer for Hyperspectral Image Classification

Feb 02, 2026

This work addresses the challenges of hyperspectral image classification, including high spectral dimensionality, complex spectral-spatial correlations, and limited labeled samples, which hinder existing Transformer models from balancing spectral discriminability and computational efficiency. To this end, we propose DSXFormer, which introduces a novel Dual-pooling Spectral Compression-Expansion (DSX) module that integrates global average and max pooling to enhance spectral channel recalibration. Additionally, a Dynamic Contextual Attention (DCA) mechanism is designed to efficiently model local spectral-spatial dependencies within a windowed Transformer framework while reducing computational overhead. Coupled with a multi-scale patch extraction and merging strategy, DSXFormer achieves state-of-the-art classification accuracies of 99.95%, 98.91%, 99.85%, and 98.52% on the Salinas, Indian Pines, Pavia University, and Kennedy Space Center benchmark datasets, respectively, significantly outperforming existing methods.

0 citationsRead paper

Systemic Risk in the European Insurance Sector

May 05, 2025

This study investigates the dynamic risk spillover mechanisms between the European insurance sector and equity, bond, and banking markets, examining the sector’s active role in systemic risk transmission. Method: Employing an extended time-varying generalized forecast error variance decomposition (GFEVD) framework—novelly integrating multidimensional performance and risk metrics—and complementing it with firm-level panel modeling. Results: The insurance sector exhibits significant net risk exports during the subprime crisis, European sovereign debt crisis, and COVID-19 pandemic. Reinsurers and diversified conglomerates serve as critical transmission nodes; systemically important insurers form a highly interconnected cluster, while subsectors display marked heterogeneity in spillover patterns. The findings challenge the conventional view of insurers as passive risk absorbers, instead establishing their proactive systemic role. This work provides a microfoundation for macroprudential policy and delivers a targeted identification tool for systemic risk monitoring.

0 citationsRead paper

Recent publications

Latest Papers

RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation

Aug 12, 2026

This work addresses the longstanding challenge in real-time speech enhancement of simultaneously achieving high audio quality and low latency. To this end, it introduces Mamba—a state space model—into this domain for the first time, proposing a fully causal architecture built upon causal time-frequency Mamba blocks. To mitigate computational overhead, the authors devise a progressive knowledge distillation strategy that jointly transfers both spectral outputs and intermediate representations from an 8-layer teacher model to a single-layer student model. Evaluated on the Voicebank-DEMAND dataset, the distilled student model achieves a PESQ score of 3.18—improved from 3.06—with only 25 ms of latency and a 2.75× speedup in inference, significantly outperforming current state-of-the-art approaches.

0 citationsRead paper

DSXFormer: Dual-Pooling Spectral Squeeze-Expansion and Dynamic Context Attention Transformer for Hyperspectral Image Classification

Feb 02, 2026

This work addresses the challenges of hyperspectral image classification, including high spectral dimensionality, complex spectral-spatial correlations, and limited labeled samples, which hinder existing Transformer models from balancing spectral discriminability and computational efficiency. To this end, we propose DSXFormer, which introduces a novel Dual-pooling Spectral Compression-Expansion (DSX) module that integrates global average and max pooling to enhance spectral channel recalibration. Additionally, a Dynamic Contextual Attention (DCA) mechanism is designed to efficiently model local spectral-spatial dependencies within a windowed Transformer framework while reducing computational overhead. Coupled with a multi-scale patch extraction and merging strategy, DSXFormer achieves state-of-the-art classification accuracies of 99.95%, 98.91%, 99.85%, and 98.52% on the Salinas, Indian Pines, Pavia University, and Kennedy Space Center benchmark datasets, respectively, significantly outperforming existing methods.

0 citationsRead paper

Systemic Risk in the European Insurance Sector

May 05, 2025

This study investigates the dynamic risk spillover mechanisms between the European insurance sector and equity, bond, and banking markets, examining the sector’s active role in systemic risk transmission. Method: Employing an extended time-varying generalized forecast error variance decomposition (GFEVD) framework—novelly integrating multidimensional performance and risk metrics—and complementing it with firm-level panel modeling. Results: The insurance sector exhibits significant net risk exports during the subprime crisis, European sovereign debt crisis, and COVID-19 pandemic. Reinsurers and diversified conglomerates serve as critical transmission nodes; systemically important insurers form a highly interconnected cluster, while subsectors display marked heterogeneity in spillover patterns. The findings challenge the conventional view of insurers as passive risk absorbers, instead establishing their proactive systemic role. This work provides a microfoundation for macroprudential policy and delivers a targeted identification tool for systemic risk monitoring.

0 citationsRead paper