Selected work

Representative Papers

A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging

Jul 30, 2026

This study addresses the lack of a standardized benchmark for fair comparison among deep learning models in multi-task 3D brain tumor segmentation. For the first time, it systematically evaluates the performance of five prominent architectures—3D U-Net, SegResNet, Swin UNETR, SegMamba, and SegMambaV2—under identical conditions, including the same dataset (BraTS 2023/2024), preprocessing pipeline, training protocol, and evaluation metrics. Through comprehensive assessment across multiple dimensions—segmentation accuracy, inference time, and model size—the work elucidates the inherent trade-offs between accuracy and efficiency. These findings provide clinically relevant guidance for model selection and deployment, effectively establishing a much-needed standardized reference framework in the field.

0 citationsRead paper

Physics-Informed Diffusion for Biomechanically Plausible 3D Sign Language Generation

Jul 16, 2026

This work addresses the common imbalance in existing 3D sign language generation methods between semantic fidelity and biomechanical plausibility, which often results in unnatural motions such as skeletal drift, joint violations, and rigid finger movements. To resolve this, we propose PIDiffSign—a physics-informed diffusion model incorporating anatomical constraints—built upon a Transformer encoder-decoder architecture that embeds biomechanical priors directly into both the diffusion process and training objective, thereby enabling the first joint optimization of semantic alignment and kinematic realism. Leveraging timestep-adaptive normalization, a differentiable geometric module, a contrastive lexical-pose alignment loss, and classifier-free guidance sampling, our method significantly outperforms current diffusion-based baselines on the PHOENIX14T and CSL-Daily benchmarks, achieving consistent improvements in pose accuracy, joint angle correctness, motion distribution fidelity, and back-translation quality.

0 citationsRead paper

Beyond the Beta Lorenz Curve: A New Parametric Family for Poverty and Inequality Estimation

Apr 01, 2026

This study addresses a critical flaw in the existing Beta Lorenz curve, whose parameter space fails to satisfy the theoretical constraints inherent to Lorenz curves, leading to systematic bias in estimating poverty and inequality from grouped income data. The authors explicitly identify this deficiency for the first time and propose a novel four-parameter family of Lorenz curves that rigorously adheres to all formal properties of genuine Lorenz curves while retaining practical usability. Through parametric modeling, derivation of necessary constraints, and extensive empirical validation across more than 2,000 datasets, the new model demonstrates superior performance in estimating poverty and inequality metrics. Specifically, it significantly reduces the systematic underestimation of poverty levels observed in over 80% of cases compared to the widely used General Quadratic (GQ) Lorenz curve.

0 citationsRead paper

Emotional Modulation in Swarm Decision Dynamics

Mar 10, 2026

This study investigates how emotion influences the formation of group consensus, with a focus on its roles in recruitment and inhibition mechanisms. By incorporating emotional valence and arousal into a swarm decision-making model, the authors develop an extended agent-based framework that integrates simulated facial expressions to model emotional contagion. For the first time, emotional dimensions are embedded into the classical swarm equations, revealing that collective decisions are jointly driven by emotional asymmetry and nonlinear amplification within the system. The results demonstrate that emotional modulation can significantly bias decision outcomes and alter convergence speed; notably, even under emotionally symmetric conditions, the system achieves rapid consensus through a nonlinear “snowball effect.”

0 citationsRead paper

Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations

Mar 06, 2026

This study addresses the challenge of balancing computational efficiency and uncertainty quantification in regional sea surface temperature forecasting by proposing a homogeneous ensemble method based on graph neural networks. During inference, structured input perturbations—such as low-resolution or fractal Perlin noise—are applied to the initial ocean state to generate ensemble forecasts without requiring additional training. Experimental results demonstrate that these spatially coherent perturbations significantly outperform random Gaussian noise, yielding better-calibrated probabilistic forecasts, lower Continuous Ranked Probability Scores (CRPS), and improved spread-skill ratios over a 15-day forecast horizon, while maintaining deterministic accuracy comparable to that of a single model. These findings highlight the critical role of perturbation structure and scale in enhancing probabilistic forecast performance.

0 citationsRead paper

Recent publications

Latest Papers

A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging

Jul 30, 2026

This study addresses the lack of a standardized benchmark for fair comparison among deep learning models in multi-task 3D brain tumor segmentation. For the first time, it systematically evaluates the performance of five prominent architectures—3D U-Net, SegResNet, Swin UNETR, SegMamba, and SegMambaV2—under identical conditions, including the same dataset (BraTS 2023/2024), preprocessing pipeline, training protocol, and evaluation metrics. Through comprehensive assessment across multiple dimensions—segmentation accuracy, inference time, and model size—the work elucidates the inherent trade-offs between accuracy and efficiency. These findings provide clinically relevant guidance for model selection and deployment, effectively establishing a much-needed standardized reference framework in the field.

0 citationsRead paper

Physics-Informed Diffusion for Biomechanically Plausible 3D Sign Language Generation

Jul 16, 2026

This work addresses the common imbalance in existing 3D sign language generation methods between semantic fidelity and biomechanical plausibility, which often results in unnatural motions such as skeletal drift, joint violations, and rigid finger movements. To resolve this, we propose PIDiffSign—a physics-informed diffusion model incorporating anatomical constraints—built upon a Transformer encoder-decoder architecture that embeds biomechanical priors directly into both the diffusion process and training objective, thereby enabling the first joint optimization of semantic alignment and kinematic realism. Leveraging timestep-adaptive normalization, a differentiable geometric module, a contrastive lexical-pose alignment loss, and classifier-free guidance sampling, our method significantly outperforms current diffusion-based baselines on the PHOENIX14T and CSL-Daily benchmarks, achieving consistent improvements in pose accuracy, joint angle correctness, motion distribution fidelity, and back-translation quality.

0 citationsRead paper

Beyond the Beta Lorenz Curve: A New Parametric Family for Poverty and Inequality Estimation

Apr 01, 2026

This study addresses a critical flaw in the existing Beta Lorenz curve, whose parameter space fails to satisfy the theoretical constraints inherent to Lorenz curves, leading to systematic bias in estimating poverty and inequality from grouped income data. The authors explicitly identify this deficiency for the first time and propose a novel four-parameter family of Lorenz curves that rigorously adheres to all formal properties of genuine Lorenz curves while retaining practical usability. Through parametric modeling, derivation of necessary constraints, and extensive empirical validation across more than 2,000 datasets, the new model demonstrates superior performance in estimating poverty and inequality metrics. Specifically, it significantly reduces the systematic underestimation of poverty levels observed in over 80% of cases compared to the widely used General Quadratic (GQ) Lorenz curve.

0 citationsRead paper

Emotional Modulation in Swarm Decision Dynamics

Mar 10, 2026

This study investigates how emotion influences the formation of group consensus, with a focus on its roles in recruitment and inhibition mechanisms. By incorporating emotional valence and arousal into a swarm decision-making model, the authors develop an extended agent-based framework that integrates simulated facial expressions to model emotional contagion. For the first time, emotional dimensions are embedded into the classical swarm equations, revealing that collective decisions are jointly driven by emotional asymmetry and nonlinear amplification within the system. The results demonstrate that emotional modulation can significantly bias decision outcomes and alter convergence speed; notably, even under emotionally symmetric conditions, the system achieves rapid consensus through a nonlinear “snowball effect.”

0 citationsRead paper

Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations

Mar 06, 2026

This study addresses the challenge of balancing computational efficiency and uncertainty quantification in regional sea surface temperature forecasting by proposing a homogeneous ensemble method based on graph neural networks. During inference, structured input perturbations—such as low-resolution or fractal Perlin noise—are applied to the initial ocean state to generate ensemble forecasts without requiring additional training. Experimental results demonstrate that these spatially coherent perturbations significantly outperform random Gaussian noise, yielding better-calibrated probabilistic forecasts, lower Continuous Ranked Probability Scores (CRPS), and improved spread-skill ratios over a 15-day forecast horizon, while maintaining deterministic accuracy comparable to that of a single model. These findings highlight the critical role of perturbation structure and scale in enhancing probabilistic forecast performance.

0 citationsRead paper