Selected work

Representative Papers

Kolmogorov Arnold Networks and Multi-Layer Perceptrons: A Paradigm Shift in Neural Modelling

Jan 15, 2026

This study addresses the longstanding trade-off between accuracy and efficiency in conventional neural networks by systematically comparing Kolmogorov–Arnold Networks (KANs) with Multilayer Perceptrons (MLPs). Built upon the Kolmogorov representation theorem, KANs employ learnable spline-based activation functions within a grid-structured architecture, achieving both high accuracy and low computational cost. Experimental results across diverse tasks—including nonlinear function approximation, time series forecasting, and multivariate classification—demonstrate that KANs consistently outperform MLPs in predictive performance while significantly reducing floating-point operations (FLOPs). These findings position KANs as an interpretable, efficient, and accurate alternative architecture, particularly well-suited for resource-constrained and real-time applications.

0 citationsRead paper

DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation

Oct 12, 2025

To address the challenge of modeling cross-domain non-uniform stylistic variations in underwater image synthesis—caused by optical phenomena such as color attenuation and turbidity—this paper proposes a style-content disentangled generative framework. Methodologically, it introduces K-means clustering for adaptive style-domain partitioning, employs a dual-branch encoder to separately extract disentangled style and content latent representations, and utilizes Adaptive Instance Normalization (AdaIN) for fine-grained style-feature fusion. The key contribution lies in the first integration of clustering-guided domain partitioning with explicit style-content disentanglement, significantly enhancing generalization across diverse underwater environments. Quantitative evaluation demonstrates state-of-the-art synthesis fidelity: SSIM = 0.9012, PSNR = 32.51 dB, and FID = 13.37.

0 citationsRead paper

Adaptive Cruise Control in Autonomous Vehicles: Challenges, Gaps, Comprehensive Review, and, Future Directions

Sep 30, 2025

Existing adaptive cruise control (ACC) research exhibits systemic gaps in safety, robustness, and urban cooperative driving, with insufficient deep analysis of critical challenges and integrated solutions. This paper employs a systematic literature review to construct a multidimensional analytical framework spanning perception–decision–control layers, thereby identifying six major research gaps in ACC for the first time. Building on this analysis, we propose an evolutionary pathway toward sustainable, fault-tolerant intelligent transportation systems—encompassing dynamic environment adaptation, human-vehicle mixed traffic coordination, and lightweight robust control. We further establish an implementable ACC research taxonomy and optimization framework. Our work addresses key limitations of prior surveys in problem depth, solution integration, and engineering feasibility, providing both theoretical foundations and practical technical guidance for next-generation ACC system design. (149 words)

0 citationsRead paper

Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints

Aug 14, 2025

To address the challenge of balancing efficiency and accuracy for large language models (LLMs) under resource constraints, this paper introduces a “computational economics” framework: modeling the LLM as an agent-based economy composed of attention heads and neuron blocks. It employs differentiable computational cost modeling and end-to-end incentive-driven training to achieve sparse activation during training and Pareto-optimal efficiency–accuracy trade-offs. The method integrates attention reallocation analysis with computation-cost regularization, enabling dynamic resource scheduling—outperforming post-hoc pruning. On GLUE and WikiText-103, it reduces FLOPS by nearly 40% and inference latency while preserving accuracy, and yields more interpretable attention patterns. The core innovation lies in the first application of economic incentive mechanisms to LLM computational resource optimization, enabling differentiable, trainable, and interpretable efficient inference.

0 citationsRead paper

Digital Natives, Digital Activists: Youth, Social Media and the Rise of Environmental Sustainability Movements

May 15, 2025

This study examines core challenges impeding youth (16–25 years) engagement in environmental action on social media: online fatigue, algorithmic platform constraints, and online-offline disconnection. Employing a mixed-methods approach—integrating formative visual narrative analysis, social media ethnography, cross-platform hashtag diffusion analysis, and participatory action research—the study proposes a dual-dimensional theoretical framework of “algorithmic inclusivity” and “climate care literacy.” It is the first systematic investigation to elucidate how visual storytelling, hashtag activism, and cross-platform coordination enhance youth environmental agency. Empirical findings demonstrate that integrated online-offline strategies increase sustained youth participation by 37%. Based on these results, the study develops a replicable digital environmental mobilization model structured around three principles: low entry barriers, high emotional resonance, and strong relational connectivity. This model offers both theoretical grounding and actionable design pathways for sustaining youth climate engagement.

0 citationsRead paper

Recent publications

Latest Papers

Kolmogorov Arnold Networks and Multi-Layer Perceptrons: A Paradigm Shift in Neural Modelling

Jan 15, 2026

This study addresses the longstanding trade-off between accuracy and efficiency in conventional neural networks by systematically comparing Kolmogorov–Arnold Networks (KANs) with Multilayer Perceptrons (MLPs). Built upon the Kolmogorov representation theorem, KANs employ learnable spline-based activation functions within a grid-structured architecture, achieving both high accuracy and low computational cost. Experimental results across diverse tasks—including nonlinear function approximation, time series forecasting, and multivariate classification—demonstrate that KANs consistently outperform MLPs in predictive performance while significantly reducing floating-point operations (FLOPs). These findings position KANs as an interpretable, efficient, and accurate alternative architecture, particularly well-suited for resource-constrained and real-time applications.

0 citationsRead paper

DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation

Oct 12, 2025

To address the challenge of modeling cross-domain non-uniform stylistic variations in underwater image synthesis—caused by optical phenomena such as color attenuation and turbidity—this paper proposes a style-content disentangled generative framework. Methodologically, it introduces K-means clustering for adaptive style-domain partitioning, employs a dual-branch encoder to separately extract disentangled style and content latent representations, and utilizes Adaptive Instance Normalization (AdaIN) for fine-grained style-feature fusion. The key contribution lies in the first integration of clustering-guided domain partitioning with explicit style-content disentanglement, significantly enhancing generalization across diverse underwater environments. Quantitative evaluation demonstrates state-of-the-art synthesis fidelity: SSIM = 0.9012, PSNR = 32.51 dB, and FID = 13.37.

0 citationsRead paper

Adaptive Cruise Control in Autonomous Vehicles: Challenges, Gaps, Comprehensive Review, and, Future Directions

Sep 30, 2025

Existing adaptive cruise control (ACC) research exhibits systemic gaps in safety, robustness, and urban cooperative driving, with insufficient deep analysis of critical challenges and integrated solutions. This paper employs a systematic literature review to construct a multidimensional analytical framework spanning perception–decision–control layers, thereby identifying six major research gaps in ACC for the first time. Building on this analysis, we propose an evolutionary pathway toward sustainable, fault-tolerant intelligent transportation systems—encompassing dynamic environment adaptation, human-vehicle mixed traffic coordination, and lightweight robust control. We further establish an implementable ACC research taxonomy and optimization framework. Our work addresses key limitations of prior surveys in problem depth, solution integration, and engineering feasibility, providing both theoretical foundations and practical technical guidance for next-generation ACC system design. (149 words)

0 citationsRead paper

Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints

Aug 14, 2025

To address the challenge of balancing efficiency and accuracy for large language models (LLMs) under resource constraints, this paper introduces a “computational economics” framework: modeling the LLM as an agent-based economy composed of attention heads and neuron blocks. It employs differentiable computational cost modeling and end-to-end incentive-driven training to achieve sparse activation during training and Pareto-optimal efficiency–accuracy trade-offs. The method integrates attention reallocation analysis with computation-cost regularization, enabling dynamic resource scheduling—outperforming post-hoc pruning. On GLUE and WikiText-103, it reduces FLOPS by nearly 40% and inference latency while preserving accuracy, and yields more interpretable attention patterns. The core innovation lies in the first application of economic incentive mechanisms to LLM computational resource optimization, enabling differentiable, trainable, and interpretable efficient inference.

0 citationsRead paper

Digital Natives, Digital Activists: Youth, Social Media and the Rise of Environmental Sustainability Movements

May 15, 2025

This study examines core challenges impeding youth (16–25 years) engagement in environmental action on social media: online fatigue, algorithmic platform constraints, and online-offline disconnection. Employing a mixed-methods approach—integrating formative visual narrative analysis, social media ethnography, cross-platform hashtag diffusion analysis, and participatory action research—the study proposes a dual-dimensional theoretical framework of “algorithmic inclusivity” and “climate care literacy.” It is the first systematic investigation to elucidate how visual storytelling, hashtag activism, and cross-platform coordination enhance youth environmental agency. Empirical findings demonstrate that integrated online-offline strategies increase sustained youth participation by 37%. Based on these results, the study develops a replicable digital environmental mobilization model structured around three principles: low entry barriers, high emotional resonance, and strong relational connectivity. This model offers both theoretical grounding and actionable design pathways for sustaining youth climate engagement.

0 citationsRead paper