Institution profile

University of Hull

Academic institutioneurope · gb
Official website
Research library34linked papers
Opportunities0open roles
Selected work

Representative Papers

SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models

May 28, 2025arXiv.org

Current large language models (LLMs) lack sufficient Simulink-domain pretraining data, rendering them unreliable for generating complete, executable Simulink simulation models directly from natural-language requirements. To address this, we propose the first multimodal agent framework specifically designed for Simulink modeling. Our approach integrates graph-structured visual understanding of Simulink diagrams, a domain-specific knowledge base, and a modular role-based collaboration mechanism—featuring specialized agents such as an investigator and a debug locator—to enable interpretable and reproducible end-to-end model generation. Crucially, the framework jointly models the visual representation and symbolic logic of Simulink models, supporting automated generation, debugging, and formal verification of simulation models from textual specifications. Evaluated on representative control and signal processing tasks, our method achieves significant improvements in code generation accuracy and structural completeness, demonstrating both technical efficacy and engineering practicality.

1 citationsRead paper

Human-Centered Explainable AI for TinyML Edge Devices: A Pareto-Based Selection Framework with LLM-Guided Design

Aug 07, 2026

This work addresses the challenge of simultaneously satisfying interpretability requirements and deployment constraints on resource-limited TinyML edge devices in clinical settings. It proposes a human-centered, multi-objective framework for selecting explainable AI (XAI) methods, which leverages large language models (LLMs) to map users’ qualitative preferences to candidate XAI techniques. By integrating feasibility filtering with Pareto optimization, the framework achieves a principled trade-off among explanation quality, stability, and deployment cost. Evaluated on a skin lesion classification task, the approach successfully identifies Pareto-efficient XAI configurations, systematically uncovering the inherent trade-offs between performance and resource expenditure across different explanation methods.

0 citationsRead paper

Knowledge-Optimising Investment Decisions with Informative Datasets

Aug 06, 2026

This study addresses the limitations of traditional investment approaches that utilize data solely for asset pricing while neglecting its systematic impact on portfolio construction and performance attribution under real-world constraints, often leading to suboptimal decisions. To overcome this, the paper proposes a novel three-stage knowledge-optimization framework encompassing decision architecture design, portfolio selection, and performance evaluation. For the first time, it integrates data, models, and business insights into actionable knowledge units embedded throughout the investment process. The framework innovatively introduces a knowledge-augmented proxy for the ex-ante Sharpe ratio to enhance knowledge-driven performance attribution. Empirical results across multiple scenarios demonstrate that the proposed method significantly elevates the explicit knowledge value in investment decisions, yielding improved portfolio performance and interpretability under practical constraints.

0 citationsRead paper
Recent publications

Latest Papers

Human-Centered Explainable AI for TinyML Edge Devices: A Pareto-Based Selection Framework with LLM-Guided Design

Aug 07, 2026

This work addresses the challenge of simultaneously satisfying interpretability requirements and deployment constraints on resource-limited TinyML edge devices in clinical settings. It proposes a human-centered, multi-objective framework for selecting explainable AI (XAI) methods, which leverages large language models (LLMs) to map users’ qualitative preferences to candidate XAI techniques. By integrating feasibility filtering with Pareto optimization, the framework achieves a principled trade-off among explanation quality, stability, and deployment cost. Evaluated on a skin lesion classification task, the approach successfully identifies Pareto-efficient XAI configurations, systematically uncovering the inherent trade-offs between performance and resource expenditure across different explanation methods.

0 citationsRead paper

Knowledge-Optimising Investment Decisions with Informative Datasets

Aug 06, 2026

This study addresses the limitations of traditional investment approaches that utilize data solely for asset pricing while neglecting its systematic impact on portfolio construction and performance attribution under real-world constraints, often leading to suboptimal decisions. To overcome this, the paper proposes a novel three-stage knowledge-optimization framework encompassing decision architecture design, portfolio selection, and performance evaluation. For the first time, it integrates data, models, and business insights into actionable knowledge units embedded throughout the investment process. The framework innovatively introduces a knowledge-augmented proxy for the ex-ante Sharpe ratio to enhance knowledge-driven performance attribution. Empirical results across multiple scenarios demonstrate that the proposed method significantly elevates the explicit knowledge value in investment decisions, yielding improved portfolio performance and interpretability under practical constraints.

0 citationsRead paper

Open Information: A Defining Perspective on Web Datasets for Carbon Pricing

Aug 05, 2026

This study investigates the impact of online data—such as social media and news—on carbon market prices and introduces a novel category of “open information” that lies between public and private information. By integrating GDELT global event data with European Union Allowance (EUA) spot prices, the authors employ vector autoregressive (VAR) and GARCH-X models to conduct statistical tests and forecast returns. The research provides the first theoretical framework and empirical evidence supporting the incorporation of large-scale online data as an alternative information source in asset pricing. Findings demonstrate that open information exerts a statistically significant influence on carbon prices, thereby validating its efficacy in financial pricing and investment decision-making.

0 citationsRead paper