Selected work

Representative Papers

QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement

Jun 16, 2026

This work addresses the challenge of balancing model efficiency and performance in high-fidelity speech enhancement by proposing QC-GAN, a novel framework that integrates quaternion representations with the Conformer architecture for the first time. By leveraging Hamiltonian products to jointly model magnitude and phase in a structured manner, QC-GAN preserves their intrinsic correlation while substantially reducing parameter count. The approach further incorporates the MetricGAN training strategy and a metric learning-based discriminator to optimize perceptual quality. On the VoiceBank+DEMAND dataset, the model achieves a PESQ score of 3.48 with only 0.89 million parameters, and even a compact 35K-parameter variant attains 3.23—significantly outperforming conventional methods. Strong generalization capability is also demonstrated on the DNS-Challenge 3 benchmark.

0 citationsRead paper

Quaternion Self-Attention with Shared Scores

May 24, 2026

Existing quaternion self-attention mechanisms compute attention scores independently for each quaternion component, resulting in high computational overhead and inconsistent attention distributions. This work proposes a shared-score quaternion self-attention mechanism that generates a single real-valued attention score via quaternion inner product and shares the resulting attention distribution across all components. Theoretical analysis reveals that when queries and keys are pre-mixed through quaternion linear projections, component-wise independent scoring and shared scoring operate within the same interaction subspace, with the former merely constituting a reparameterization of the latter without enhancing representational capacity. Experiments demonstrate that the proposed method reduces GPU and CPU inference time by 44.3% and 58.1%, respectively, on speech enhancement tasks while maintaining performance, and consistently yields advantages across vision and natural language processing benchmarks.

0 citationsRead paper

Implementing Errors on Errors: Bayesian vs Frequentist

May 10, 2025

To address the lack of theoretical foundation for “uncertainty in uncertainties” in experimental data fusion, this paper establishes a unified probabilistic framework that rigorously models uncertainty in quoted variances, thereby bridging the conceptual gap between Bayesian and frequentist approaches. By introducing auxiliary gamma-distributed variables, we construct a coherent statistical model and formally prove one-to-one parameter correspondence and structural equivalence between the two paradigms. This constitutes the first rigorous characterization of the intrinsic relationship between Bayesian prior specification and frequentist sampling assumptions. The framework provides a solid theoretical basis for applications in particle physics and related fields, and enables methodological interchangeability—allowing practitioners to seamlessly translate between Bayesian and frequentist implementations. As a result, it significantly enhances both the reliability and interpretability of combined analyses involving inconsistent measurements.

0 citationsRead paper

Recent publications

Latest Papers

QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement

Jun 16, 2026

This work addresses the challenge of balancing model efficiency and performance in high-fidelity speech enhancement by proposing QC-GAN, a novel framework that integrates quaternion representations with the Conformer architecture for the first time. By leveraging Hamiltonian products to jointly model magnitude and phase in a structured manner, QC-GAN preserves their intrinsic correlation while substantially reducing parameter count. The approach further incorporates the MetricGAN training strategy and a metric learning-based discriminator to optimize perceptual quality. On the VoiceBank+DEMAND dataset, the model achieves a PESQ score of 3.48 with only 0.89 million parameters, and even a compact 35K-parameter variant attains 3.23—significantly outperforming conventional methods. Strong generalization capability is also demonstrated on the DNS-Challenge 3 benchmark.

0 citationsRead paper

Quaternion Self-Attention with Shared Scores

May 24, 2026

Existing quaternion self-attention mechanisms compute attention scores independently for each quaternion component, resulting in high computational overhead and inconsistent attention distributions. This work proposes a shared-score quaternion self-attention mechanism that generates a single real-valued attention score via quaternion inner product and shares the resulting attention distribution across all components. Theoretical analysis reveals that when queries and keys are pre-mixed through quaternion linear projections, component-wise independent scoring and shared scoring operate within the same interaction subspace, with the former merely constituting a reparameterization of the latter without enhancing representational capacity. Experiments demonstrate that the proposed method reduces GPU and CPU inference time by 44.3% and 58.1%, respectively, on speech enhancement tasks while maintaining performance, and consistently yields advantages across vision and natural language processing benchmarks.

0 citationsRead paper

Implementing Errors on Errors: Bayesian vs Frequentist

May 10, 2025

To address the lack of theoretical foundation for “uncertainty in uncertainties” in experimental data fusion, this paper establishes a unified probabilistic framework that rigorously models uncertainty in quoted variances, thereby bridging the conceptual gap between Bayesian and frequentist approaches. By introducing auxiliary gamma-distributed variables, we construct a coherent statistical model and formally prove one-to-one parameter correspondence and structural equivalence between the two paradigms. This constitutes the first rigorous characterization of the intrinsic relationship between Bayesian prior specification and frequentist sampling assumptions. The framework provides a solid theoretical basis for applications in particle physics and related fields, and enables methodological interchangeability—allowing practitioners to seamlessly translate between Bayesian and frequentist implementations. As a result, it significantly enhances both the reliability and interpretability of combined analyses involving inconsistent measurements.

0 citationsRead paper