arXiv subjects

Zhiming Zhao

Publications and source records attributed to Zhiming Zhao.

At least 19 recordsLinked to original sources

arXiv2026

A Multi-Viewpoint Modeling Framework for Digital Twin Integration and Reuse with LLM-Assisted Compatibility Analysis

Digital Twin (DT) ecosystems integrate heterogeneous computational models to represent complex systems under evolving, purpose-specific objectives. Systematic reuse of existing high-quality models and datasets is essential for scalable DT development, yet is constrained by heterogeneity in semantic intent, data structures, behavioral interfaces, and execution environments. As a result, integration becomes a cross-model, cross-view consistency problem that is hard to predict, quantify, and compare across design choices. Existing standards and integration platforms address these concerns separately, offering limited support for structured, purpose-aware compatibility assessment and early feasibility analysis when models are reused under new DT objectives. This paper introduces a multi-viewpoint integration modeling framework grounded in the Reference Model of Open Distributed Processing (RM-ODP). The framework structures integration-relevant knowledge across domain, information, computational, engineering, and technology viewpoints, representing cross-view dependencies as explicit, machine-actionable metadata. It comprises (i) a viewpoint-structured Model Metamodel for systematic model description and discovery, and (ii) a pattern-aware Mismatch Detector that operationalizes cross-view compatibility constraints via integration patterns, combining deterministic rule generation with Large Language Model (LLM)-assisted reasoning. This enables systematic identification of semantic, informational, and runtime inconsistencies and supports reasoning about integration feasibility and effort before implementation. Expert validation and an environmental modeling case study show that the approach enables structured compatibility reasoning, improves transparency of integration assumptions, strengthens cross-view interoperability, and supports scalable reuse in heterogeneous DT ecosystems.

cs.SE↗

arXiv2026

From Metrics to Improvement: A Lifecycle-Aware LLM Feedback Framework for Research Software Quality

Research software is increasingly central to scientific workflows, yet it is often developed by researchers with limited software engineering expertise. This can lead to quality issues that hinder maintainability, reproducibility, reuse, and sustainability. Existing static analysis tools can identify such issues, but their outputs often require expert interpretation and provide limited support for translating quality assessments into actionable improvements. To address this gap, we propose a lifecycle-aware framework that integrates quantitative software quality assessment with Large Language Model (LLM)-based code refinement. The framework comprises two stages. First, a lifecycle-aware Quality Model is developed from established software quality standards and practitioner requirements. The model defines five quality dimensions and 25 candidate metrics, of which 14 are operationalized using existing analysis tools and custom measurements. Second, the resulting quality diagnostics are used as structured feedback within an iterative LLM-based refinement process, enabling generated improvements to be repeatedly reassessed against the Quality Model. We evaluate the framework on notebook-centric research software using multiple LLMs and compare iterative structured feedback with single-step feedback and unstructured prompting. The results show improvements in specific quality attributes, particularly code duplication and structural quality, while also revealing trade-offs among maintainability, code size, documentation, and complexity. These findings demonstrate the potential of metric-driven LLM feedback for research software quality improvement while highlighting its inherently multi-objective nature \footnote{The source code and experimental data are publicly available at https://github.com/QCDIS/Software_Quality_Control_LLM . }

cs.SE↗

arXiv2026

An AI-Assisted Migration Framework for Transforming Legacy Scientific Applications into Reusable Cloud-Based Workflows

Legacy scientific applications remain valuable research assets but are often tightly coupled to project-specific execution environments, limiting their reuse, reproducibility, and deployment within modern scientific workflow systems and cloud-native Virtual Research Environments (VREs). Existing migration approaches primarily target individual artifacts, such as notebooks or containers, and provide limited support for systematically transforming heterogeneous legacy applications into reusable cloud-native workflows. This paper presents an AI-assisted migration framework that combines the Reference Model of Open Distributed Processing (RM-ODP)-guided architectural analysis, Large Language Models (LLMs), and Design Structure Matrix (DSM) analysis. The framework first uses RM-ODP to guide an LLM in identifying reusable workflow components, their interfaces, and execution dependencies from heterogeneous legacy applications. The resulting workflow structure is then iteratively evaluated and refined using DSM analysis. Finally, an LLM-based workflow generator implements the validated workflow components and produces containerized execution environments and executable workflow definitions for deployment in cloud-native workflow systems, including VREs. The framework was evaluated on two legacy scientific applications from different scientific domains. In both cases, the applications were successfully transformed into reusable cloud-native workflows while preserving their original functionality, demonstrating the feasibility of the proposed approach for modernizing legacy scientific software.

cs.SE↗

arXiv2026

LLMCrater: Lifecycle-Aware FAIR Metadata Generation using Large Language Models

FAIR (Findable, Accessible, Interoperable, and Reusable) metadata is essential for the discovery, interoperability, and reuse of scientific research assets. However, creating and maintaining FAIR metadata remains largely manual, making the process time-consuming for heterogeneous research artifacts generated throughout the research lifecycle. Existing approaches primarily generate metadata at publication time, missing opportunities to capture contextual information as it becomes available. To address this limitation, we present \emph{LLMCrater}, a lifecycle-aware metadata generation framework that combines Large Language Models (LLMs) with stage-specific RO-Crate metadata profiles. The framework progressively enriches metadata across four research lifecycle stages (Design, Development, Deployment, and Execution \& Provenance) while remaining compatible with RO-Crate~1.1 and EOSC metadata recommendations. It automatically extracts metadata from heterogeneous artifacts, generates and validates machine-actionable RO-Crates, and supports publication to FAIR repositories and PID services (e.g., Zenodo). We demonstrate the approach using two representative use cases: a 5G experimentation environment within SLICES-RI and an experiment on GreenDIGIT's EcoJupyter platform. Results show that LLMCrater progressively enriches metadata throughout the research lifecycle and generates valid RO-Crates conforming to the RO-Crate~1.1 specification.

cs.SE↗

arXiv2026

Social Hippocampus Memory Learning

Social learning highlights that learning agents improve not in isolation, but through interaction and structured knowledge exchange with others. When introduced into machine learning, this principle gives rise to social machine learning (SML), where multiple agents collaboratively learn by sharing abstracted knowledge. Federated learning (FL) provides a natural collaboration substrate for this paradigm, yet existing heterogeneous FL approaches often rely on sharing model parameters or intermediate representations, which may expose sensitive information and incur additional overhead. In this work, we propose SoHip (Social Hippocampus Memory Learning), a memory-centric social machine learning framework that enables collaboration among heterogeneous agents via memory sharing rather than model sharing. SoHip abstracts each agent's individual short-term memory from local representations, consolidates it into individual long-term memory through a hippocampus-inspired mechanism, and fuses it with collectively aggregated long-term memory to enhance local prediction. Throughout the process, raw data and local models remain on-device, while only lightweight memory are exchanged. We provide theoretical analysis on convergence and privacy preservation properties. Experiments on two benchmark datasets with seven baselines demonstrate that SoHip consistently outperforms existing methods, achieving up to 8.78% accuracy improvements.

cs.LG↗

arXiv2026

Unveiling the Security Risks of Federated Learning in the Wild: From Research to Practice

Federated learning (FL) has attracted substantial attention in both academia and industry, yet its practical security posture remains poorly understood. In particular, a large body of poisoning research is evaluated under idealized assumptions about attacker participation, client homogeneity, and success metrics, which can substantially distort how security risks are perceived in deployed FL systems. This paper revisits FL security from a measurement perspective. We systematize three major sources of mismatch between research and practice: unrealistic poisoning threat models, the omission of hybrid heterogeneity, and incomplete metrics that overemphasize peak attack success while ignoring stability and utility cost. To study these gaps, we build TFLlib, a uniform evaluation framework that supports image, text, and tabular FL tasks and re-implements representative poisoning attacks under practical settings. Our empirical study shows that idealized evaluation often overstates security risk. Under practical settings, attack performance becomes markedly more dataset-dependent and unstable, and several attacks that appear consistently strong in idealized FL lose effectiveness or incur clear benign-task degradation once practical constraints are enforced. These findings further show that final-round attack success alone is insufficient for security assessment; practical measurement must jointly consider effectiveness, temporal stability, and collateral utility loss. Overall, this work argues that many conclusions in the FL poisoning literature are not directly transferable to real deployments. By tightening the threat model and using measurement protocols aligned with practice, we provide a more realistic view of the security risks faced by contemporary FL systems and distill concrete guidance for future FL security evaluation. Our code is available at https://github.com/xaddwell/TFLlib

cs.CR↗

arXiv2026

Helix: A Dual-Helix Co-Evolutionary Multi-Agent System for Prompt Optimization and Question Reformulation

Automated prompt optimization (APO) aims to improve large language model performance by refining prompt instructions. However, existing methods are largely constrained by fixed prompt templates, limited search spaces, or single-sided optimization that treats user questions as immutable inputs. In practice, question formulation and prompt design are inherently interdependent: clearer question structures facilitate focused reasoning and task understanding, while effective prompts reveal better ways to organize and restate queries. Ignoring this coupling fundamentally limits the effectiveness and adaptability of current APO approaches. We propose a unified multi-agent system (Helix) that jointly optimizes question reformulation and prompt instructions through a structured three-stage co-evolutionary framework. Helix integrates (1) planner-guided decomposition that breaks optimization into coupled question-prompt objectives, (2) dual-track co-evolution where specialized agents iteratively refine and critique each other to produce complementary improvements, and (3) strategy-driven question generation that instantiates high-quality reformulations for robust inference. Extensive experiments on 12 benchmarks against 6 strong baselines demonstrate the effectiveness of Helix, achieving up to 3.95% performance improvements across tasks with favorable optimization efficiency.

cs.MA↗

arXiv2026

FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment

Aligning large language models (LLMs) with human preferences in federated learning (FL) is challenging due to decentralized, privacy-sensitive, and highly non-IID preference data. Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning with human feedback (RLHF), but its direct application in FL suffers from severe performance degradation under non-IID data and limited generalization of implicit rewards. To bridge this gap, we propose FedPDPO (Federated Personalized Direct Preference Optimization), a personalized federated framework for preference alignment of LLMs. It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation. To address non-IID heterogeneity, we devise (1) the globally shared LoRA adapter with the personalized client-specific LLM head. Moreover, we introduce (2) a personalized DPO training strategy with a client-specific explicit reward head to complement implicit rewards and further alleviate non-IID heterogeneity, and (3) a bottleneck adapter to balance global and local features. We provide theoretical analysis establishing the probabilistic foundation and soundness. Extensive experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.

cs.LG↗

arXiv2025

How Reliable are LLMs for Reasoning on the Re-ranking task?

With the improving semantic understanding capability of Large Language Models (LLMs), they exhibit a greater awareness and alignment with human values, but this comes at the cost of transparency. Although promising results are achieved via experimental analysis, an in-depth understanding of the LLM's internal workings is unavoidable to comprehend the reasoning behind the re-ranking, which provides end users with an explanation that enables them to make an informed decision. Moreover, in newly developed systems with limited user engagement and insufficient ranking data, accurately re-ranking content remains a significant challenge. While various training methods affect the training of LLMs and generate inference, our analysis has found that some training methods exhibit better explainability than others, implying that an accurate semantic understanding has not been learned through all training methods; instead, abstract knowledge has been gained to optimize evaluation, which raises questions about the true reliability of LLMs. Therefore, in this work, we analyze how different training methods affect the semantic understanding of the re-ranking task in LLMs and investigate whether these models can generate more informed textual reasoning to overcome the challenges of transparency or LLMs and limited training data. To analyze the LLMs for re-ranking tasks, we utilize a relatively small ranking dataset from the environment and the Earth science domain to re-rank retrieved content. Furthermore, we also analyze the explainable information to see if the re-ranking can be reasoned using explainability.

cs.CL↗

arXiv2025

How good are LLMs at Retrieving Documents in a Specific Domain?

Classical search engines using indexing methods in data infrastructures primarily allow keyword-based queries to retrieve content. While these indexing-based methods are highly scalable and efficient, due to a lack of an appropriate evaluation dataset and a limited understanding of semantics, they often fail to capture the user's intent and generate incomplete responses during evaluation. This problem also extends to domain-specific search systems that utilize a Knowledge Base (KB) to access data from various research infrastructures. Research infrastructures (RIs) from the environmental and earth science domain, which encompass the study of ecosystems, biodiversity, oceanography, and climate change, generate, share, and reuse large volumes of data. While there are attempts to provide a centralized search service using Elasticsearch as a knowledge base, they also face similar challenges in understanding queries with multiple intents. To address these challenges, we proposed an automated method to curate a domain-specific evaluation dataset to analyze the capability of a search system. Furthermore, we incorporate the Retrieval of Augmented Generation (RAG), powered by Large Language Models (LLMs), for high-quality retrieval of environmental domain data using natural language queries. Our quantitative and qualitative analysis of the evaluation dataset shows that LLM-based systems for information retrieval return results with higher precision when understanding queries with multiple intents, compared to Elasticsearch-based systems.

cs.IR↗

arXiv2025

Dynamically evolving segment anything model with continuous learning for medical image segmentation

Medical image segmentation is essential for clinical diagnosis, surgical planning, and treatment monitoring. Traditional approaches typically strive to tackle all medical image segmentation scenarios via one-time learning. However, in practical applications, the diversity of scenarios and tasks in medical image segmentation continues to expand, necessitating models that can dynamically evolve to meet the demands of various segmentation tasks. Here, we introduce EvoSAM, a dynamically evolving medical image segmentation model that continuously accumulates new knowledge from an ever-expanding array of scenarios and tasks, enhancing its segmentation capabilities. Extensive evaluations on surgical image blood vessel segmentation and multi-site prostate MRI segmentation demonstrate that EvoSAM not only improves segmentation accuracy but also mitigates catastrophic forgetting. Further experiments conducted by surgical clinicians on blood vessel segmentation confirm that EvoSAM enhances segmentation efficiency based on user prompts, highlighting its potential as a promising tool for clinical applications.

cs.CV↗

arXiv2025

Managing Federated Learning on Decentralized Infrastructures as a Reputation-based Collaborative Workflow

Federated Learning (FL) has recently emerged as a collaborative learning paradigm that can train a global model among distributed participants without raw data exchange to satisfy varying requirements. However, there remain several challenges in managing FL in a decentralized environment, where potential candidates exhibit varying motivation levels and reliability in the FL process management: 1) reconfiguring and automating diverse FL workflows are challenging, 2) difficulty in incentivizing potential candidates with high-quality data and high-performance computing to join the FL, and 3) difficulty in ensuring reliable system operations, which may be vulnerable to various malicious attacks from FL participants. To address these challenges, we focus on the workflow-based methods to automate diverse FL pipelines and propose a novel approach to facilitate reliable FL system operations with robust mechanism design and blockchain technology by considering a contribution model, fair committee selection, dynamic reputation updates, reward and penalty methods, and contract theory. Moreover, we study the optimality of contracts to guide the design and implementation of smart contracts that can be deployed in blockchain networks. We perform theoretical analysis and conduct extensive simulation experiments to validate the proposed approach. The results show that our incentive mechanisms are feasible and can achieve fairness in reward allocation in unreliable environment settings.

cs.DC↗

arXiv2025

CrowdAL: Towards a Blockchain-empowered Active Learning System in Crowd Data Labeling

Active Learning (AL) is a machine learning technique where the model selectively queries the most informative data points for labeling by human experts. Integrating AL with crowdsourcing leverages crowd diversity to enhance data labeling but introduces challenges in consensus and privacy. This poster presents CrowdAL, a blockchain-empowered crowd AL system designed to address these challenges. CrowdAL integrates blockchain for transparency and a tamper-proof incentive mechanism, using smart contracts to evaluate crowd workers' performance and aggregate labeling results, and employs zero-knowledge proofs to protect worker privacy.

cs.CR↗

arXiv2024

PriCE: Privacy-Preserving and Cost-Effective Scheduling for Parallelizing the Large Medical Image Processing Workflow over Hybrid Clouds

Running deep neural networks for large medical images is a resource-hungry and time-consuming task with centralized computing. Outsourcing such medical image processing tasks to hybrid clouds has benefits, such as a significant reduction of execution time and monetary cost. However, due to privacy concerns, it is still challenging to process sensitive medical images over clouds, which would hinder their deployment in many real-world applications. To overcome this, we first formulate the overall optimization objectives of the privacy-preserving distributed system model, i.e., minimizing the amount of information about the private data learned by the adversaries throughout the process, reducing the maximum execution time and cost under the user budget constraint. We propose a novel privacy-preserving and cost-effective method called PriCE to solve this multi-objective optimization problem. We performed extensive simulation experiments for artifact detection tasks on medical images using an ensemble of five deep convolutional neural network inferences as the workflow task. Experimental results show that PriCE successfully splits a wide range of input gigapixel medical images with graph-coloring-based strategies, yielding desired output utility and lowering the privacy risk, makespan, and monetary cost under user's budget.

cs.CE↗

arXiv2024

D-VRE: From a Jupyter-enabled Private Research Environment to Decentralized Collaborative Research Ecosystem

Today, scientific research is increasingly data-centric and compute-intensive, relying on data and models across distributed sources. However, it still faces challenges in the traditional cooperation mode, due to the high storage and computing cost, geo-location barriers, and local confidentiality regulations. The Jupyter environment has recently emerged and evolved as a vital virtual research environment for scientific computing, which researchers can use to scale computational analyses up to larger datasets and high-performance computing resources. Nevertheless, existing approaches lack robust support of a decentralized cooperation mode to unlock the full potential of decentralized collaborative scientific research, e.g., seamlessly secure data sharing. In this work, we change the basic structure and legacy norms of current research environments via the seamless integration of Jupyter with Ethereum blockchain capabilities. As such, it creates a Decentralized Virtual Research Environment (D-VRE) from private computational notebooks to decentralized collaborative research ecosystem. We propose a novel architecture for the D-VRE and prototype some essential D-VRE elements for enabling secure data sharing with decentralized identity, user-centric agreement-making, membership, and research asset management. To validate our method, we conducted an experimental study to test all functionalities of D-VRE smart contracts and their gas consumption. In addition, we deployed the D-VRE prototype on a test net of the Ethereum blockchain for demonstration. The feedback from the studies showcases the current prototype's usability, ease of use, and potential and suggests further improvements.

cs.DC↗

arXiv2024

Towards Privacy-, Budget-, and Deadline-Aware Service Optimization for Large Medical Image Processing across Hybrid Clouds

Efficiently processing medical images, such as whole slide images in digital pathology, is essential for timely diagnosing high-risk diseases. However, this demands advanced computing infrastructure, e.g., GPU servers for deep learning inferencing, and local processing is time-consuming and costly. Besides, privacy concerns further complicate the employment of remote cloud infrastructures. While previous research has explored privacy and security-aware workflow scheduling in hybrid clouds for distributed processing, privacy-preserving data splitting, optimizing the service allocation of outsourcing computation on split data to the cloud, and privacy evaluation for large medical images still need to be addressed. This study focuses on tailoring a virtual infrastructure within a hybrid cloud environment and scheduling the image processing services while preserving privacy. We aim to minimize the use of untrusted nodes, lower monetary costs, and reduce execution time under privacy, budget, and deadline requirements. We consider a two-phase solution and develop 1) a privacy-preserving data splitting algorithm and 2) a greedy Pareto front-based algorithm for optimizing the service allocation. We conducted experiments with real and simulated data to validate and compare our method with a baseline. The results show that our privacy mechanism design outperforms the baseline regarding the average lower band on individual privacy and information gain for privacy evaluation. In addition, our approach can obtain various Pareto optimal-based allocations with users' preferences on the maximum number of untrusted nodes, budget, and time threshold. Our solutions often dominate the baseline's solution and are superior on a tight budget. Specifically, our approach has been ahead of baseline, up to 85.2% and 6.8% in terms of the total financial and time costs, respectively.

cs.DC↗

arXiv2024

Towards Seamless Serverless Computing Across an Edge-Cloud Continuum

Serverless computing has emerged as an attractive paradigm due to the efficiency of development and the ease of deployment without managing any underlying infrastructure. Nevertheless, serverless computing approaches face numerous challenges to unlock their full potential in hybrid environments. To gain a deeper understanding and firsthand knowledge of serverless computing in edge-cloud deployments, we review the current state of open-source serverless platforms and compare them based on predefined requirements. We then design and implement a serverless computing platform with a novel edge orchestration technique that seamlessly deploys serverless functions across the edge and cloud environments on top of the Knative serverless platform. Moreover, we propose an offloading strategy for edge environments and four different functions for experimentation and showcase the performance benefits of our solution. Our results demonstrate that such an approach can efficiently utilize both cloud and edge resources by dynamically offloading functions from the edge to the cloud during high activity, while reducing the overall application latency and increasing request throughput compared to an edge-only deployment.

cs.DC↗

arXiv2023

Ocean Data Quality Assessment through Outlier Detection-enhanced Active Learning

Ocean and climate research benefits from global ocean observation initiatives such as Argo, GLOSS, and EMSO. The Argo network, dedicated to ocean profiling, generates a vast volume of observatory data. However, data quality issues from sensor malfunctions and transmission errors necessitate stringent quality assessment. Existing methods, including machine learning, fall short due to limited labeled data and imbalanced datasets. To address these challenges, we propose an ODEAL framework for ocean data quality assessment, employing AL to reduce human experts' workload in the quality assessment workflow and leveraging outlier detection algorithms for effective model initialization. We also conduct extensive experiments on five large-scale realistic Argo datasets to gain insights into our proposed method, including the effectiveness of AL query strategies and the initial set construction approach. The results suggest that our framework enhances quality assessment efficiency by up to 465.5% with the uncertainty-based query strategy compared to random sampling and minimizes overall annotation costs by up to 76.9% using the initial set built with outlier detectors.

cs.LG↗