An Agentic RAG and Evaluation Framework for Assurance Case Generation: Industrial Use Case for the EU Cyber Resilience Act Compliance
本文针对中小企业遵守欧盟网络安全韧性法案的挑战，提出了一种基于代理增强生成和自然语言推理评估框架自动生成合规性案例的方法，以减少手动工作并保持决策透明。
0 citationsRead paper
Selected work
Representative Papers
Real-Time State-of-Health Estimation and Online Degradation Prognosis from Partial Battery Discharge Using Physics-Informed Neural Networks
This study addresses the limitations of fixed discharge protocols and real-time prediction challenges in lithium-ion battery state-of-health (SOH) estimation by proposing a novel framework integrating physical mechanisms with deep learning. By constructing a physics-informed neural network that utilizes partial discharge curves from arbitrary voltage intervals, the method enables adaptive monitoring without requiring prior knowledge or extensive historical data. This approach overcomes traditional protocol constraints, achieving a mean absolute percentage error below 4% under complex operating conditions while accurately capturing critical aging transitions in real time. Consequently, the proposed framework significantly enhances the flexibility and reliability of battery lifecycle management, offering a robust solution for practical deployment where standardized testing is infeasible.
0 citationsRead paper
Is Synthetic Image Augmentation Useful for Imbalanced Classification Problems? Case-Study on the MIDOG2025 Atypical Cell Detection Competition
This work addresses the detection of rare, clinically critical asymmetric mitotic cells in histopathological images—challenged by severe class imbalance and cross-center domain shift. We systematically evaluate synthetic data augmentation and pretraining strategies, employing ConvNeXt-Small and Lunit’s self-supervised ViT as backbones, with five-fold cross-validation and joint training on real and synthetic samples. Results show that domain-specific pretraining enhances robustness, while ImageNet pretraining achieves higher performance ceilings; naive synthetic augmentation yields limited and inconsistent gains. The two models achieve a mean AUROC of 95%, with ConvNeXt attaining the highest AUROC (95.4%) on the held-out test set and Lunit demonstrating superior balanced accuracy. Our study uncovers the trade-off between pretraining source and data augmentation efficacy for rare pathological object recognition, offering a reproducible methodological framework for few-shot classification in medical imaging.
0 citationsRead paper
GeLaCo: An Evolutionary Approach to Layer Compression
Deploying large language models (LLMs) incurs substantial computational overhead, and existing structured pruning methods rely on time-consuming empirical search, often failing to identify globally optimal compression configurations. Method: This paper proposes a layer-wise compression framework based on multi-objective evolutionary optimization. It is the first to explicitly construct the Pareto frontier between compression ratio and model quality, integrating population-based evolution, layer-folding strategies, and modular similarity metrics—spanning attention mechanisms, feed-forward networks, and hidden states—to enable efficient, interpretable, and fully automated compression. Contribution/Results: The framework outperforms state-of-the-art methods on both base and instruction-tuned LLMs. Perplexity and generation capability evaluations demonstrate that it maintains high performance while achieving significant parameter reduction, validating its effectiveness and generalizability.
0 citationsRead paper
Exploring the application of quantum technologies to industrial and real-world use cases
Current NISQ-era quantum hardware suffers from high noise and limited qubit counts, hindering direct solution of industrially relevant problems of moderate complexity. Method: This work proposes a production-oriented hybrid quantum-classical paradigm integrating high-connectivity superconducting/ion-trap devices, a lightweight domain-specific programming framework, and an out-of-the-box algorithm library. It targets three representative application domains—quantum-enhanced machine learning, combinatorial optimization, and quantum chemistry simulation—and establishes end-to-end deployable workflows. Contribution/Results: The approach substantially lowers the barrier to quantum adoption for industrial users. It delivers the first systematic experimental validation of feasibility and quantum speedup pathways across multiple problem classes on real NISQ hardware. By providing a reusable technical stack—including hardware-agnostic abstractions, optimized compilation, and validated application templates—this work bridges the gap between quantum laboratory research and industrial deployment, offering concrete implementation blueprints for near-term quantum advantage.
0 citationsRead paper
Recent publications
Latest Papers
An Agentic RAG and Evaluation Framework for Assurance Case Generation: Industrial Use Case for the EU Cyber Resilience Act Compliance
本文针对中小企业遵守欧盟网络安全韧性法案的挑战，提出了一种基于代理增强生成和自然语言推理评估框架自动生成合规性案例的方法，以减少手动工作并保持决策透明。
0 citationsRead paper
Real-Time State-of-Health Estimation and Online Degradation Prognosis from Partial Battery Discharge Using Physics-Informed Neural Networks
This study addresses the limitations of fixed discharge protocols and real-time prediction challenges in lithium-ion battery state-of-health (SOH) estimation by proposing a novel framework integrating physical mechanisms with deep learning. By constructing a physics-informed neural network that utilizes partial discharge curves from arbitrary voltage intervals, the method enables adaptive monitoring without requiring prior knowledge or extensive historical data. This approach overcomes traditional protocol constraints, achieving a mean absolute percentage error below 4% under complex operating conditions while accurately capturing critical aging transitions in real time. Consequently, the proposed framework significantly enhances the flexibility and reliability of battery lifecycle management, offering a robust solution for practical deployment where standardized testing is infeasible.
0 citationsRead paper
Is Synthetic Image Augmentation Useful for Imbalanced Classification Problems? Case-Study on the MIDOG2025 Atypical Cell Detection Competition
This work addresses the detection of rare, clinically critical asymmetric mitotic cells in histopathological images—challenged by severe class imbalance and cross-center domain shift. We systematically evaluate synthetic data augmentation and pretraining strategies, employing ConvNeXt-Small and Lunit’s self-supervised ViT as backbones, with five-fold cross-validation and joint training on real and synthetic samples. Results show that domain-specific pretraining enhances robustness, while ImageNet pretraining achieves higher performance ceilings; naive synthetic augmentation yields limited and inconsistent gains. The two models achieve a mean AUROC of 95%, with ConvNeXt attaining the highest AUROC (95.4%) on the held-out test set and Lunit demonstrating superior balanced accuracy. Our study uncovers the trade-off between pretraining source and data augmentation efficacy for rare pathological object recognition, offering a reproducible methodological framework for few-shot classification in medical imaging.
0 citationsRead paper
GeLaCo: An Evolutionary Approach to Layer Compression
Deploying large language models (LLMs) incurs substantial computational overhead, and existing structured pruning methods rely on time-consuming empirical search, often failing to identify globally optimal compression configurations. Method: This paper proposes a layer-wise compression framework based on multi-objective evolutionary optimization. It is the first to explicitly construct the Pareto frontier between compression ratio and model quality, integrating population-based evolution, layer-folding strategies, and modular similarity metrics—spanning attention mechanisms, feed-forward networks, and hidden states—to enable efficient, interpretable, and fully automated compression. Contribution/Results: The framework outperforms state-of-the-art methods on both base and instruction-tuned LLMs. Perplexity and generation capability evaluations demonstrate that it maintains high performance while achieving significant parameter reduction, validating its effectiveness and generalizability.
0 citationsRead paper
Exploring the application of quantum technologies to industrial and real-world use cases
Current NISQ-era quantum hardware suffers from high noise and limited qubit counts, hindering direct solution of industrially relevant problems of moderate complexity. Method: This work proposes a production-oriented hybrid quantum-classical paradigm integrating high-connectivity superconducting/ion-trap devices, a lightweight domain-specific programming framework, and an out-of-the-box algorithm library. It targets three representative application domains—quantum-enhanced machine learning, combinatorial optimization, and quantum chemistry simulation—and establishes end-to-end deployable workflows. Contribution/Results: The approach substantially lowers the barrier to quantum adoption for industrial users. It delivers the first systematic experimental validation of feasibility and quantum speedup pathways across multiple problem classes on real NISQ hardware. By providing a reusable technical stack—including hardware-agnostic abstractions, optimized compilation, and validated application templates—this work bridges the gap between quantum laboratory research and industrial deployment, offering concrete implementation blueprints for near-term quantum advantage.
0 citationsRead paper