--Deep neural networks (DNNs) enhance the accuracy and efficiency of reconstructing key parameters from time-resolved photon arrival signals recorded by single-photon detectors. However, the performance of conventional backpropagation-based DNNs is highly dependent on various parameters of the optical setup and biological samples under examination, necessitating frequent network retraining--either through transfer learning or from scratch. Newly collected data must also be stored and transferred to a high-performance GPU server for retraining, introducing latency and storage overhead. T o address these challenges, we propose an online training algorithm based on a One-Sided Jacobi rotation-based Online Sequential Extreme Learning Machine (OSOS-ELM). We fully exploit parallelism in executing OSOS-ELM on a heterogeneous FPGA with integrated ARM cores. Extensive evaluations of OSOS-ELM and OS-ELM demonstrate that both achieve comparable accuracy across different network dimensions (i.e., input, hidden, and output layers), while OSOS-ELM proves to be more hardware-efficient. By leveraging the parallelism of OSOS-ELM, we implement a holistic computing prototype on a Xilinx ZCU104 FPGA, which integrates a multi-core CPU and programmable logic fabric. We also implement our OSOS-ELM on the NVIDIA Jetson Xavier NX GPU to comprehensively investigate its computing performance on another type of heterogeneous computing platform. N-device training of neural networks has been emerging in recent decades. On-device training and inference save the overhead of data transfer to data centers, memory management, and computing on the cloud. The number of edge devices is increasing exponentially and is expected to reach 1 trillion by 2035 [1]. Latency tends to be a bottleneck of real-time applications such as healthcare and machine automation. Additionally, information privacy can be threatened when uploading and offloading sensitive biomedical data to the cloud. This work is supported by the EPSRC (EP/T00097X/1); the Quantum Technology Hub in Quantum Imaging (QuantiC), and the University of Strathclyde. Xingda Li also acknowledges support from China Scholarship Council.

To complete an open-ended programming exercise, students need to both plan a high-level solution and implement it using the appropriate syntax. However, these problems are often autograded on the correctness of the final submission through test cases, and students cannot get feedback on their planning process. Large language models (LLM) may be able to generate this feedback by detecting the overall code structure even for submissions with syntax errors. To this end, we propose an approach that detects which high-level goals and patterns (i.e. programming plans) exist in a student program with LLMs. We show that both the full GPT-4o model and a small variant (GPT-4o-mini) can detect these plans with remarkable accuracy, outperforming baselines inspired by conventional approaches to code analysis. We further show that the smaller, cost-effective variant (GPT-4o-mini) achieves results on par with state-of-the-art (GPT-4o) after fine-tuning, creating promising implications for smaller models for real-time grading. These smaller models can be incorporated into autograders for open-ended code-writing exercises to provide feedback for students' implicit planning skills, even when their program is syntactically incorrect. Furthermore, LLMs may be useful in providing feedback for problems in other domains where students start with a set of high-level solution steps and iteratively compute the output, such as math and physics problems.

Digital elevation models derived from Interferometric Synthetic Aperture Radar (InSAR) data over glacial and snow-covered regions often exhibit systematic elevation errors, commonly termed "penetration bias. " W e leverage existing physics-based models and propose an integrated correction framework that combines parametric physical modeling with machine learning. W e evaluate the approach across three distinct training scenarios -- each defined by a different set of acquisition parameters -- to assess overall performance and the model's ability to generalize. Our experiments on Greenland's ice sheet using T anDEM-X data show that the proposed hybrid model corrections significantly reduce the mean and standard deviation of DEM errors compared to a purely physical modeling baseline. The hybrid framework also achieves significantly improved generalization than a pure ML approach when trained on data with limited diversity in acquisition parameters.

Leveraging this'adaptive' potential of medical ML could generate significant benefits for patient health and well-being. Recent engagements with the ethical issues generated by the use of adaptive ML systems in medicine have typically been limited to discussions of'the update problem': how should systems that continue to change and evolve post-regulatory approval be regulated? In this paper, we draw attention to an important set of ethical issues raised by the use of adaptive machine learning systems in medicine that have, thus far, been neglected and are highly deserving of further attention. Discussions of adaptive machine learning systems to date have overlooked the distinction between two sorts of variance that such systems may exhibit -- diachronic evolution (change over time) and synchronic variation (difference between cotempo-raneous instantiations of the algorithmic system at different sites) -- and underestimated the significance of the latter. Both diachronic evolution and synchronic variation will complicate the hermeneutic task of clinicians in interpreting the outputs of AI systems, and will therefore pose significant challenges to the process of securing informed consent to treatment. Equity issues may occur where synchronic variation is permitted, as the quality of care may vary significantly across patients or between hospitals. However, the decision as to whether to allow or eliminate synchronic variation involves complex trade-offs between accuracy and generalisability, as well as a number of other values, including justice and non-maleficence. In some contexts, preventing synchronic variation from emerging may only be possible at the expense of the wellbeing, and the quality of care available to, particular patients or classes of patients. Designers and regulators of adaptive ML systems will need to confront these issues if the potential benefits of adaptive ML in medical care are to be realised.

We introduce AI University (AI-U), a flexible framework for AI-driven course content delivery that adapts to instructors' teaching styles. At its core, AI-U fine-tunes a large language model (LLM) with retrieval-augmented generation (RAG) to generate instructor-aligned responses from lecture videos, notes, and textbooks. Using a graduate-level finite-element-method (FEM) course as a case study, we present a scalable pipeline to systematically construct training data, fine-tune an open-source LLM with Low-Rank Adaptation (LoRA), and optimize its responses through RAG-based synthesis. Our evaluation - combining cosine similarity, LLM-based assessment, and expert review - demonstrates strong alignment with course materials. We also have developed a prototype web application, available at https://my-ai-university.com, that enhances traceability by linking AI-generated responses to specific sections of the relevant course material and time-stamped instances of the open-access video lectures. Our expert model is found to have greater cosine similarity with a reference on 86% of test cases. An LLM judge also found our expert model to outperform the base Llama 3.2 model approximately four times out of five. AI-U offers a scalable approach to AI-assisted education, paving the way for broader adoption in higher education. Here, our framework has been presented in the setting of a class on FEM - a subject that is central to training PhD and Master students in engineering science. However, this setting is a particular instance of a broader context: fine-tuning LLMs to research content in science.

The availability and abundance of GenAI tools to administer tasks traditionally managed by people have raised concerns, particularly within the education and academic sectors, as some students may highly rely on these tools to complete the assignments designed to enable learning. This article focuses on informing students about the significance of investing their time during their studies on developing essential life-long learning skills using their own critical thinking, rather than depending on AI models that are susceptible to misinformation, hallucination, and bias. As we transition to an AI-centric era, it is important to educate students on how these models work, their pitfalls, and the ethical concerns associated with feeding data to such tools. Keywords: GenAI in Academic Writing GenAI's Ethics GenAI's Privacy Concerns. 1 Introduction Writing academic reports, and papers have been instrumental to assisting students and researchers in shaping their ideas, organising their methods, and practicing their communication skills, particularly when this process is combined with receiving constant feedback from experts. With the launch of OpenAI's first publicly available Large Language Model, namely ChatGPT (GPT-3.5), a significant concern rose within the academic and research community about the reliability of the academic and research output. Evidence suggests that as individuals began discovering the availability and efficiency in using Generative Artificial Intelligence tools in late 2022, there was a significant surge in retracted research articles resulting in more than 10,000 retracted papers [1]. The over-reliance of individuals on various Generative Artificial Intelligence (Gen AI) tools for completing tasks that require a human's critical thinking has raised concerns.

As Large Language Models (LLMs) more deeply integrate into human life across various regions, aligning them with pluralistic cultures is crucial for improving user experience and mitigating cultural conflicts. Existing approaches develop culturally aligned LLMs primarily through fine-tuning with massive carefully curated culture-specific corpora. Nevertheless, inspired by culture theories, we identify two key challenges faced by these datasets: (1) Representativeness: These corpora fail to fully capture the target culture's core characteristics with redundancy, causing computation waste; (2) Distinctiveness: They struggle to distinguish the unique nuances of a given culture from shared patterns across other relevant ones, hindering precise cultural modeling. To handle these challenges, we introduce CAReDiO, a novel cultural data construction framework. Specifically, CAReDiO utilizes powerful LLMs to automatically generate cultural conversation data, where both the queries and responses are further optimized by maximizing representativeness and distinctiveness. Using CAReDiO, we construct a small yet effective dataset, covering five cultures, and compare it with several recent cultural corpora. Extensive experiments demonstrate that our method generates more effective data and enables cultural alignment with as few as 100 training samples, enhancing both performance and efficiency.

As LLMs grow in capability, the task of supervising LLMs becomes more challenging. Supervision failures can occur if LLMs are sensitive to factors that supervisors are unaware of. We investigate Mechanistic Anomaly Detection (MAD) as a technique to augment supervision of capable models; we use internal model features to identify anomalous training signals so they can be investigated or discarded. We train detectors to flag points from the test environment that differ substantially from the training environment, and experiment with a large variety of detector features and scoring rules to detect anomalies in a set of "quirky" language models. We find that detectors can achieve high discrimination on some tasks, but no detector is effective across all models and tasks. MAD techniques may be effective in low-stakes applications, but advances in both detection and evaluation are likely needed if they are to be used in high stakes settings. Large language models (LLMs) excel at a wide range of tasks, yet as their capabilities grow, ensuring effective human oversight becomes increasingly challenging. These considerations have motivated Mechanistic Anomaly Detection (MAD): instead of attempting to understand all facets of a model's internal reasoning, MAD focuses on extracting a signal that indicates when an episode is anomalous--flagging behaviors that deviate from the expected patterns without assuming specific trigger mechanisms (Christiano, 2022). This signal could be used to filter out anomalous episodes, or to trigger deeper investigation.

Estimating item difficulty through field-testing is often resource-intensive and time-consuming. As such, there is strong motivation to develop methods that can predict item difficulty at scale using only the item content. Large Language Models (LLMs) represent a new frontier for this goal. The present research examines the feasibility of using an LLM to predict item difficulty for K-5 mathematics and reading assessment items (N = 5170). Two estimation approaches were implemented: (a) a direct estimation method that prompted the LLM to assign a single difficulty rating to each item, and (b) a feature-based strategy where the LLM extracted multiple cognitive and linguistic features, which were then used in ensemble tree-based models (random forests and gradient boosting) to predict difficulty. Overall, direct LLM estimates showed moderate to strong correlations with true item difficulties. However, their accuracy varied by grade level, often performing worse for early grades. In contrast, the feature-based method yielded stronger predictive accuracy, with correlations as high as r = 0.87 and lower error estimates compared to both direct LLM predictions and baseline regressors. These findings highlight the promise of LLMs in streamlining item development and reducing reliance on extensive field testing and underscore the importance of structured feature extraction. We provide a seven-step workflow for testing professionals who would want to implement a similar item difficulty estimation approach with their item pool.

ABSTRACT The growing complexity of construction management (CM) projects, coupled with challenges such as strict regulatory requirements and labor shortages, requires specialized analytical tools that streamline project workflow and enhance performance. Although large language models (LLMs) have demonstrated exceptional performance in general reasoning tasks, their effectiveness in tackling CM-specific challenges, such as precise quantitative analysis and regulatory interpretation, remains inadequately explored. To bridge this gap, this study introduces CMExamSet, a comprehensive benchmarking dataset comprising 689 authentic multiple-choice questions sourced from 1 arXiv:2504.08779v1 The results indicate that GPT-4o and Claude 3.7 surpass typical human pass thresholds (70%), with average accuracies of 82% and 83%, respectively. Additionally, both models performed better on single-step tasks, with accuracies of 85.7% (GPT-4o) and 86.7% (Claude 3.7). Multi-step tasks were more challenging, reducing performance to 76.5% and 77.6%, respectively. Our error pattern analysis further reveals that conceptual misunderstandings are the most common (44.4% and 47.9%), underscoring the need for enhanced domain-specific reasoning models. These findings underscore the potential of LLMs as valuable supplementary analytical tools in CM, while highlighting the need for domain-specific refinements and sustained human oversight in complex decision making. INTRODUCTION The construction industry is undergoing a transformation driven by digital technologies, increased project complexity, heterogeneous regulations, and ongoing labor shortages (Abioye et al. 2021). These changes create a pressing need for intelligent tools that can augment human expertise and support decision-making in construction management (CM) (Regona et al. 2022). Among these technologies, large language models (LLMs) such as GPT-4 and Claude have shown a comparative performance in general reasoning, natural language understanding, and educational applications (Ooi et al. 2025).