Unlocking New Potentials in Generative AI

This chapter discusses the opportunities and challenges posed by the use of generative AI in the Sharia auditing profession. Generative AI (GAI) technologies have the potential to transform the operations of the financial and auditing departments completely. In a way, they perform self-importance roles such as building insights and automating challenging tasks while enhancing decision-making in these sectors. It is evident that through the use of GAI, the power of deep learning and neural networks can be harnessed to improve business processes and monitor outliers, which are critical for achieving both compliance and transparency in finance. However, we must highlight certain drawbacks that come along when employing GAI for Sharia-compliant auditing. According to Islamic law, Sharia compliance is based on Shariah rules and laws, so the audit has to meet certain requirements. Hence, auditing has to obey certain ethical and legal aspects.Does GAI integration into Sharia-compliant audits carry a concern of operating outside the technological, ethical, and Islamic principles? Yes, it has been observed that GAI systems depend on algorithmic geography, data tenderness, and the rules of regulation for their use. Besides, the GAI uptake exposes the increasing need for Sharia data and gaps in the interpretability of existing AI models. These are some of the reasons why GAI for Sharia auditors is attractive, even as there are challenges like automation of compliance and fraud detection, and a gap in operational definitions.This chapter explores the implication of GAI on Sharia auditors in terms of contemporary practice impact, challenges like ethics and technical limitations, and new opportunities for efficiency and compliance improvements. This discussion embeds insights from recent research, including works like Rabbani et al. on the necessity for ethical frameworks relating to AI in Islamic finance and Brown et al.’s findings about advanced language models in terms of their competency for actionable insight performance. Based on these aspects, this chapter will seek an all-rounded appreciation of the challenges and opportunities generative AI does or will pose.

Generative AI is designed to create new content from trained parameters. Learning from large amounts of data, many of these models aim to simulate human conversation. Generative AI is being applied to many different sectors. Within healthcare there has been innovation specifically towards generative AI models trained on electronic medical record data. A recent review characterizes these models, their strengths, and weaknesses. Inspired by that work, we present our evaluation checklist for generative AI models applied to electronic medical records.

Claims that GPT-4 can outperform more than 90% of human test-takers in the US Uniform Bar Examination have sparked heated debates about the impact of Generative AI (GenAI) on legal education, academic integrity, and the future of legal practice. Yet GenAI’s capabilities in broader legal examination contexts – including in jurisdictions outside the US – are unclear. This study addresses this gap by evaluating GenAI’s performance against students who took the ‘Criminal Law’ final exam at an Australian law school in Spring 2023. Various AI models and prompt engineering techniques were used to generate 10 distinct answers to the exam question. Five criminal law tutors, unaware of AI involvement, graded a mix of AI-generated and student responses. Then, the tutors were briefed on the AI-generated papers they marked and engaged in reflective semi-structured interviews. The study found that GenAI performed below the student average in questions that required detailed legal and critical analysis. However, all GenAI papers performed better than students in open-ended questions and essay writing tasks. These results provide a benchmark for the capabilities and limitations of GenAI in higher education and provide insights into the potential implications of its application to legal assessments and education, curriculum development, and the future workforce.

AI models, particularly generative AI and large language models, reshape digital information ecosystems by curating and amplifying content through user engagement metrics. Despite their capacity to reduce bias and promote inclusivity, these models simultaneously amplify cognitive biases, entrench filter bubbles, and spread misinformation. The intensification of human–machine interaction and hyper-industrialization complicates this further, as large language models increasingly mediate how information is produced and consumed. Socio-technical agency describes how AI systems co-construct human behavior and societal norms through their design, yet their effects remain understudied in regions with limited technological infrastructure. This paper investigates AI’s influence on information dissemination, cognitive biases, and user agency across digital media environments in key regions of the Global South. Drawing on qualitative interviews and a survey of 580 media technology users in South Africa, Indonesia, India, the Philippines, and Brazil it examines how generative AI affects emotional engagement, exposure to content, and perceptions of digital truth. Framed by media ecology theory, the study evaluates AI as a cognitive extension that can both reinforce and challenge digital biases. The study proposes strategies for using generative AI to support information integrity while addressing the risks of polarization and exclusion. By centering perspectives from regions in the Global South, it contributes to more equitable discourse on AI governance, advocating regulatory and design solutions responsive to diverse media ecologies.

Generative artificial intelligence has become prevalent in discussions of educational technology, particularly in the context of mathematics education. These AI models can engage in human‐like conversation and generate answers to complex questions in real‐time, with education reports accentuating their potential to make teachers' work more efficient and improve student learning. This paper provides a review of the current literature on generative AI in mathematics education, focusing on four areas: generative AI for mathematics problem‐solving, generative AI for mathematics tutoring and feedback, generative AI to adapt mathematical tasks, and generative AI to assist mathematics teachers in planning. The paper discusses ethical and logistical issues that arise with the application of generative AI in mathematics education, and closes with some observations, recommendations, and future directions.

In this article, we investigate the critical intersections of AI, academic integrity, and disability in the context of a large undergraduate course. Our aim was to adapt the course to respond to generative AI (GenAI) to avoid entrenching barriers for students, and instead teach them how to use GenAI tools in ways that deepen their learning and uphold academic honesty. Grounded in disability justice and access pedagogies, we outline five design goals centered on guidelines for AI usage, education on responsible AI use, revised assessments, support for teaching assistants (TAs), and accessible materials. These activities are detailed in our methodology. In our findings, we provide a critical reflection of the course adaptation, taking up issues such as varying levels of familiarity with GenAI, students’ capacity to engage with course changes, resistance to GenAI, instructors’ relational shifts to AI, and feelings of demoralization among the teaching team. We conclude by offering practical recommendations for educators, calling for learning communities to view this disruption as an invitation to listen to disabled students.

Machine learning has surged in popularity in recent years, with deep neural networks (DNNs) becoming a cornerstone of applications such as autonomous driving, augmented reality, and natural language processing, owing to their remarkable accuracy and scalability. As the demand for greater portability and flexibility grows, there is a strong push to optimize these applications for resource-constrained edge devices like smartphones and IoT devices.However, deploying DNN models on such devices presents significant challenges, primarily due to the large size of these models, which is a key contributor to their high performance. For instance, the DeepSpeech 2 model outperforms its predecessor, DeepSpeech 1, but its size is eight times larger, encompassing approximately 68 million parameters. Similarly, other networks designed for various tasks, including convolutional neural networks like VGG and transformer-based networks like BERT and GPT, also exhibit substantial sizes. For example, the GPT-3 model, a predecessor to ChatGPT, consists of an astonishing 175 billion parameters. Consequently, fitting DNN models onto resource-limited edge devices is a formidable challenge. My thesis addresses these challenges with a three-part approach: * High-Performance DNN Accelerators: I will develop DNN accelerators that excel in high performance, low latency, and energy efficiency through an algorithm and hardware co-design across diverse FPGA architectures (Chapter 2). * Real-Time DNN Execution: I aim to achieve exceptional accuracy and real-time execution for various large-scale DNNs on off-the-shelf mobile devices, IoT devices, and other platforms (Chapter 3). * CompVQC Framework: I will explore a systematic framework, CompVQC, to reduce the circuit length of quantum neural networks (QNNs) through model compression, which can achieve up to a 20% improvement in accuracy. This reveals that compilation-aware compression can enhance the robustness of QNNs on near-term noisy quantum devices (Chapter 4). The field of AI has recently undergone a significant transformation, ushering in the era of generative AI, where models like ChatGPT and Stable Diffusion create realistic and creative content for a wide range of applications. As generative AI becomes more prevalent, it is crucial to adapt algorithm-hardware co-design strategies to meet the specific needs of these models, particularly on edge devices. In the final chapter (Chapter 5), I will introduce my ongoing and future work focused on activating generative AI on the edge.--Author's abstract

The TrollLabs Open dataset includes comprehensive information that offers a comparison of design practices and outcomes between human participants and Generative AI during a hackathon event. The dataset was curated through the running of a prototyping hackathon designed to assess the abilities and performance of generative AI, specifically ChatGPT, in the early stages of engineering design. This assessment involved comparing ChatGPT's performance to that of experienced engineering students in a hackathon setting, where participants competed by making a prototype that fires a NERF dart as far as possible. In this setup, all ideas, concepts, strategies, and actions undertaken by the AI-controlled team were autonomously generated by the ChatGPT, without human intervention or guidance, but implemented by two participants. Five self-directed baseline teams competed against the AI team. The dataset comprises 116 prototype entries and 433 edges (connection) that enable comparative analysis of design practices and performance between the team instructed solely by generative AI and baseline teams of experienced engineering design students. Prototypes and their attribute data were captured using Pro2booth, an online prototype capture platform running on participants' phones and computers. The dataset includes a transcript of the conversation between ChatGPT and the team responsible for implementing its recommendations, featuring 97 exchanges of prompts and responses. It contains the initial prompt used to instruct the AI, the objective and rules of the hackathon and the objective performance of teams, showing the ChatGPT team finishing 2nd among six teams. To the authors' knowledge, the TrollLabs Open dataset is the first and only open resource that directly compares the performance of generative AI with human teams in an engineering design context. Thus, it is intended to be a valuable resource to design researchers, engineering and design students, educators, and industry professionals seeking to find strategies for implementing generative AI tools in their design processes. By offering a comprehensive data collection, the dataset enables external researchers to conduct in-depth analyses that could highlight the practical implications of integrating generative AI in design practices, possibly providing an overview of its limitations and presenting recommendations for improved integration in the design process.

This study presents an empirical investigation into the energy consumption of discriminative and generative AI models within real-world MLOps pipelines. For discriminative models, we examine various architectures and hyperparameters during training and inference and identify energy-efficient practices. For generative AI, large language models (LLMs) are assessed, with a focus primarily on energy consumption across different model sizes and varying service requests. Our study employs software-based power measurements, ensuring ease of replication across diverse configurations, models, and datasets. We analyse multiple models and hardware setups to uncover correlations among various metrics, identifying key contributors to energy consumption. The results indicate that, for discriminative models, optimising architectures, hyperparameters, and hardware can significantly reduce energy consumption without sacrificing performance. For LLMs, energy efficiency depends on balancing model size, reasoning complexity, and request-handling capacity, as larger models do not necessarily consume more energy when utilisation remains low. This analysis provides practical guidelines for designing green and sustainable ML operations, emphasising energy consumption and carbon-footprint reductions while maintaining performance. This paper can serve as a benchmark for accurately estimating total energy use across different types of AI models.

Generative AI models represent a significant advancement in content creation capabilities but face substantial challenges when deployed at the network edge due to inherent resource constraints. This article examines comprehensive optimization strategies for enabling generative AI functionality on edge devices without requiring cloud connectivity. The exponential growth in model size has created a widening gap between computational requirements and the limited resources available in edge environments. Through systematic model compression, architectural redesign, and hardware-software co-optimization, generative models can achieve dramatic efficiency improvements while maintaining acceptable quality thresholds. The compression techniques examined include pruning methodologies that systematically eliminate redundant parameters, quantization approaches that reduce numerical precision, and knowledge distillation methods that transfer capabilities from larger models to compact alternatives. Architectural innovations such as modified attention mechanisms, conditional computation, and neural architecture search further enhance efficiency by fundamentally rethinking model design for resource-constrained environments. The integration of these techniques with hardware-specific optimizations and specialized software frameworks enables practical deployment across diverse application domains. Real-world implementations in speech processing, computer vision, and industrial IoT demonstrate that properly optimized generative models can operate within edge constraints while delivering near-real-time performance and maintaining high-quality outputs. These advancements empower industries to leverage generative AI capabilities in scenarios where privacy concerns, connectivity limitations, or latency requirements make cloud-based processing impractical.

Abstract: Augmented Human Intelligence (AHI) represents a paradigm shift in human-AI collaboration, leveraging Generative AI, Quantum Computing, and Extended Reality (XR) to enhance cognitive capabilities, decision-making, and immersive interactions. Generative AI enables real-time knowledge augmentation, automated creativity, and adaptive learning, while Quantum Computing accelerates AI optimization, pattern recognition, and complex problem-solving. XR technologies provide intuitive, immersive environments for AI-driven collaboration, bridging the gap between digital and physical experiences. The convergence of these technologies fosters hybrid intelligence, where AI amplifies human potential rather than replacing it. This research explores AI-augmented cognition, quantum-enhanced simulations, and AI-driven spatial computing, addressing ethical, security, and societal implications of human-machine synergy. By integrating decentralized AI governance, privacy-preserving AI techniques, and brain-computer interfaces, this study outlines a scalable framework for next-generation augmented intelligence applications in healthcare, enterprise intelligence, scientific discovery, and immersive learning. The future of AHI lies in hybrid intelligence systems that co-evolve with human cognition, ensuring responsible and transparent AI augmentation to unlock new frontiers in human potential. Keywords: Augmented Human Intelligence, Generative AI, Quantum Computing, Extended Reality, XR, AI-driven Cognition, Hybrid Intelligence, Brain-Computer Interfaces, AI Ethics, AI-enhanced Learning, Spatial Computing, Quantum AI, Immersive AI, Human-AI Collaboration, Ethical AI Frameworks.

Copyright protection during the training stage of generative AI: Industry-oriented U.S. law, rights-oriented EU law, and fair remuneration rights for generative AI training under the UN's international governance regime for AI

While industry practices evolve rapidly, marketing education in Australia and New Zealand faces challenges in keeping pace, particularly regarding the adoption of current marketing technologies (Harrigan et al., 2022). Generative AI, exemplified by systems like ChatGPT and DALL·E, has demonstrated benefits for learning (Baidoo-Anu & Ansah, 2023). However, despite its potential, there remains a dearth of practical guidance on effectively incorporating these technologies into marketing courses. This gap persists even as general frameworks for responsible and ethical AI use, such as the Australian Framework for Generative AI in Schools (2023), emerge. As the demand for graduates with generative AI skills grows in the job market, educators must explore innovative pedagogical approaches to bridge this gap. This academic poster presents an innovative application of generative artificial intelligence (GenAI) in the context of teaching digital marketing at the postgraduate level. Its purpose is to bridge the gap between academic theory and industry practice by encouraging educators to integrate AI tools into their curriculum through experiential learning pedagogy (Kolb, 2014), characterized by a learning process whereby knowledge is created through hands-on experiences. The poster exemplifies how various types of GenAI technologies — specifically text-based, image-based, and video-based — can enhance teaching content, tutorial exercises, and assessments within the digital marketing course. The poster showcases examples of how these GenAI tools are integrated in the course content, to guide students in generating innovative ideas for using AI in marketing to gain a competitive edge: Text-based GenAI: Tools like ChatGPT and Gemini can automatically generate search keywords for search engine marketing. By integrating text-based GenAI tools with established marketing technology (MarTech) tools such as Google Ads and Google Ads Keyword Planner, students engage in practical exercises that combine AI-generated initial ideas (e.g., search keywords) with further analysis (e.g., search volume, click-through rates, and bidding costs) using established MarTech tools. This hands-on approach enhances their learning experience and prepares them for real-world applications. Image-based GenAI: Platforms such as DALL·E, Midjourney, and Stable Diffusion enable the creation of custom images for display advertising, enhancing visual communication in marketing materials. Through experiential learning activities, students can explore ideas, seek unusual combinations, and inspire creativity faster with image-based GenAI tools, resulting in a greater variety of display ad materials. Video-based GenAI: Applications like Sora and Synthesia facilitate the production of short video clips suitable for social media marketing (e.g., YouTube Shorts, TikTok). By engaging in dynamic content creation exercises, students learn to streamline content creation, reduce manual work, and save both time and budget, thereby gaining practical skills in social media marketing. By incorporating these GenAI technologies through experiential learning pedagogy, educators can enrich the learning experience, foster critical thinking, and prepare students for the evolving landscape of digital marketing. Future research can study the use of GenAI in marketing education using theoretical frameworks such as the Unified Theory of Acceptance and Use of Technology (Venkatesh et al., 2016).

The emergence of Generative AI presents both opportunities and challenges, especially in technology enhanced learning (TEL) and open and distance learning (ODL). Guidance remains fragmented, with ethical safeguards, instructional design, and pedagogy often treated separately. This study identifies key indicators and synthesises integration of the Generative AI Integrated Framework for Education, GAIIFE, structured around three interdependent pillars: Ethical Considerations (EC), Instructional Development (ID), and Pedagogical Approach (PA). Using conceptual framework development to derive key dimensions from 17 papers, followed by a simplified Qualitative Comparative Analysis (QCA), two contrasting frameworks were compared to identify which dimensions were present or absent. One framework emphasises ethics, the other instructional design, and both omit pedagogical grounding. The Generative AI Integrated Framework for Education (GAIIFE) integrates ethical integrity, instructional alignment, and learner centred pedagogy to guide responsible Generative AI integration across educational contexts, with relevance for TEL and ODL. The framework contributes to equitable education by offering a practical guide for responsible Generative AI integration.

Background Handwritten home-based vaccination records (HBRs) are a vital source of immunization data, yet manual transcription in household surveys is time-consuming, error-prone, and resource-intensive. Recent advances in multimodal generative AI models offer a potential pathway to partially automate this task under certain conditions, improving efficiency while maintaining data quality. Methods We evaluated the performance of generative multimodal AI models, specifically OpenAI’s GPT-4o, in transcribing handwritten vaccination cards from a 2022 survey targeting children aged 12 - 35 months in The Gambia. Using a curated dataset of 335 cards (6,700 vaccination entries), we developed a gold-standard benchmark from three human transcribers (all of them in The Gambia) and assessed AI model performance across transcription accuracy, vaccination coverage estimates, timeliness, and missed opportunities for simultaneous vaccination (MOSV). We also tested a confidence-based segmentation approach to identify high-confidence transcriptions suitable for automation versus low-confidence entries requiring human review. Results The fine-tuned GPT-4o model achieved 79% accuracy for exact date transcription and reached human-level performance (94% accuracy) on 69% of entries classified by the AI as high-confidence. Coverage and timeliness estimates from high-confidence transcriptions were 98.0% and 91.6% accurate, respectively, compared to 98.8% and 95.6% from human transcribers. Date errors by AI and humans differ systematically, with AI showing fewer year-shift errors. Conclusion Multimodal AI models show strong potential for automating HBR transcription in immunization coverage surveys, at least in a setting like The Gambia. When paired with confidence-based filtering, these models achieve human-level performance on coverage and timeliness estimates—the key metrics used in programmatic decision-making—across a large subset of records. This enables substantial gains in efficiency while preserving data quality. Further research should evaluate generalizability across diverse card formats, languages, and contexts to support integration into real-world immunization programs and health monitoring activities.