Sindhi language models struggle with Romanized Sindhi as there is variation in the spellings of everyday words, and short prompts do not explicitly state the task or target language. In this study, the remaining source record of a small DeepSeek-R1 p...
Federal law and judicial rulings in the United States direct educators to provide special education services to students with disabilities that enable them to demonstrate meaningful progress, considering their circumstances. The services are to compr...
The rapid advancement of sensor technologies and deep learning has significantly advanced the field of image captioning, especially for complex scenes. Traditional image captioning methods are often unable to handle the intricacies and detailed relat...
A core feature of a multi-tiered system of supports (MTSS) is configuring instruction to match each student’s needs. For students who demonstrate academic achievement deficits and need supplemental remedial instruction, it must be coordinated a...
Standard SAM-based approaches in medical imaging typically rely on explicit geometric prompts, such as bounding boxes or points. However, these rigid spatial constraints are often insufficient for capturing the complex, deformable boundaries of medic...
Background/Objectives: In food-image nutrient estimation with vision-language models (VLMs), portion size is a dominant source of error, yet how a prompt shifts the estimated amount—and in which direction—remains uncharacterized. We teste...
The impact of Generative artificial intelligence (GAI) on footwear design creativity and feasibility was investigated in this study. Using a text-to-image GAI tool called Midjourney, 17 prompts were tested to generate footwear concepts. Ten distinct...
Referring Remote Sensing Image Segmentation (RRSIS) is a representative multimodal understanding task for remote sensing, which segments designated targets from remote images according to free-form natural language descriptions. However, complex remo...
Proactive Artificial Intelligence systems in intelligent cockpits can initiate prompts without explicit user commands, yet when such prompts should be delivered remains underexplored. This study examines how prompt timing affects user experience in a...
In complex driving environments, drivers must continuously detect and respond to critical visual information such as traffic signs and pedestrians. However, important targets may sometimes be overlooked due to high cognitive load during driving. Ther...
Test-time adaptation (TTA) has been proven to effectively improve the adaptability of deep learning semantic segmentation models facing continuous changeable scenes. However, most of the existing TTA algorithms lack an explicit exploration of domain...
To improve prompt utilization and boundary perception in SAM-based interactive medical image segmentation, this paper proposes ASAM2-UNet, a U-shaped visual foundation model built upon SAM2-UNet. Unlike methods that treat prompts as auxiliary spatial...
Large Language Models (LLMs) have rapidly become central components of cognitive computing systems and AI-assisted knowledge work. However, the effectiveness of LLM-generated outputs depends not only on the model’s capabilities but also on the...
Generative AI tutors have become a common tool for independent learning, yet their capacity to support self-regulated learning (SRL) is poorly understood. This simulation-based textual analysis of prompt design evaluates a frontier large language mod...
Large language models (LLMs) have emerged as powerful tools for (semi-)automating the initial screening of abstracts in systematic reviews, offering the potential to significantly reduce the manual burden on research teams. This paper provides a broa...
Existing studies on backdoor attacks in large language models (LLMs) have contributed significantly to the literature by exploring trigger-based strategies—such as rare tokens or syntactic anomalies—that, however, limit both their stealth...
Generative models have shown excellent results in aspect-based sentiment analysis tasks by predicting quadruples by setting specific template formats. The existing research predicts sentiment elements and enhances the dependency between elements usin...
Large Language Models (LLMs) remain highly susceptible to jailbreak attacks that bypass safety alignments through sophisticated prompt manipulation. While multi-agent defense systems have emerged as a promising countermeasure, existing frameworks pre...
Multimodal large language models (MLLMs) have become increasingly proficient at solving complex problems. Here, we systematically compare performance between humans and two of the currently most widely used MLLMs, ChatGPT-5 and Gemini 3, on mental ro...
Metacognitive monitoring plays a crucial role in self-regulated learning, as accurate monitoring enables effective control, which in turn impacts learning outcomes. Most studies on metacognitive monitoring have focused on learners’ monitoring a...
Generative artificial intelligence is reshaping how people interact with digital technologies, emphasizing the need to develop effective skills for engaging with it. In this context, prompt engineering has emerged as a critical skill for optimizing A...
An empathetic chatbot is an essential component of intelligent mental healthcare. We adopted implicitly empathy prompting (IEP) by decomposing empathy into supportive dialogue, paraphrased response, emotional understanding, and attitude expression, r...
Generative artificial intelligence is creating new possibilities for educational resource development, making prompt design increasingly relevant to interactions with these tools. However, little research has examined how pedagogical criteria are rep...
Infrared small target detection (IRSTD) supports remote-sensing surveillance and early warning, but infrared targets often occupy only a few pixels, exhibit weak appearance cues, and resemble thermal clutter. Vision-language detectors such as Groundi...
Large language models and vision–language models already achieve strong results on reasoning tasks, but their reliability under controlled assessment-style conditions remains insufficiently characterized. This paper presents a benchmark study o...
Medical Visual Question Answering (MedVQA) lies at the intersection of computer vision, natural language processing, and clinical decision-making, aiming to generate accurate responses from medical images paired with complex inquiries. Despite recent...
The rapid development of generative artificial intelligence has paved the way for a new approach to reproduce and intelligently generate traditional patterns digitally. This paper focuses on the traditional Chinese phoenix pattern and constructs a &l...
This paper explores the emerging potential of large language models (LLMs) and generative AI for social network analysis (SNA) based on open-ended survey data as a source. We introduce a novel methodology, Survey-to-Multilayer Network (SURVEY2MLN), w...
Camera-distribution monitoring and semantic out-of-distribution detection assign different meanings to weather and illumination changes. We evaluate specified departures from a camera reference distribution and distinguish the image representation fr...
15 November 2026
Automated network response must stop attacks without restricting legitimate hosts. We evaluate deterministic evidence checks applied before a source is blocked, in a pipeline that combines XGBoost flow scoring, optional arbitration by a local languag...
Background: Large language models (LLMs) are increasingly used for musculoskeletal health information, yet their safety in time-sensitive shoulder and elbow presentations with red-flag features remains insufficiently defined. We evaluated safety beha...
Large language models are increasingly consulted by cancer patients, and a single unsafe answer about chemotherapy dosing, opioid use or self-harm can cause real harm. This paper introduces a calibrated Monte-Carlo risk gate that treats colorectal-ca...
Text-to-image diffusion models such as Stable Diffusion enable high-quality image synthesis from text and are widely deployed due to their open-source nature and low computational requirements. However, this accessibility also makes them attractive t...
Few-shot open-set object detection (FS-OSOD) remains challenging in real-world scenarios, where detectors must accurately recognize known objects from few examples while reliably rejecting vast unknown categories. Under this setting, decision boundar...
This study presents a quantitative metric-based comparison of four state-of-the-art text-to-image generative AI systems for architectural visualization: OpenAI Image Generation, Imagen 4, Midjourney v8.1, and Stable Image Ultra. The models were evalu...
The rapid integration of Large Language Models (LLMs) into critical personal and professional environments has exacerbated security risks, particularly adversarial attacks such as prompt injection and jailbreaking, which aim to bypass safety alignmen...
While object detection and recognition have been extensively adopted by many applications in decision-making, new algorithms and methodologies have emerged to enhance the automatic identification of target objects. In particular, the rise of deep lea...
Implicit discourse relation recognition (IDRR) addresses the classification of discourse relations between text segments without explicit connectives. Existing prompt-based methods for IDRR often rely heavily on predicting surface connectives as an i...
Accurate tumor segmentation in 3D medical images is essential for clinical diagnosis, treatment planning, and prognosis. However, this task remains challenging due to low contrast, irregular morphology, and indistinct boundaries. Most Segment Anythin...
In this study, we employed ChatGPT, an advanced large language model, to analyze hotel reviews, focusing on aspect-based feedback to understand service failures in the hospitality industry. The shift from traditional feedback analysis methods to natu...
Few-shot remote-sensing fine-grained ship classification (RS-FGSC) faces two coupled challenges: limited annotated samples and mixed-visibility imaging conditions caused by cloud occlusion. Although CLIP-based prompt learning provides useful transfer...
Resource-constrained vision sensor systems must balance promptable concept detection, segmentation quality, and inference cost. We evaluate structured pruning and grid-preserving token-resolution restructuring of pretrained SAM 3 under prompt-count-a...
Arabic’s complex morphological system and the optional use of short vowels (tashkīl) introduce substantial lexical ambiguity, posing significant challenges for Large Language Models (LLMs). While diacritics enhance linguistic precision, LL...
The growing integration of chatbots and large language models (LLMs) into society raises important concerns about their potential to reproduce toxic human behaviors. As a result, it is essential to investigate these models to mitigate or eliminate su...
Connecting culturally informed concept design to engineering assessment requires explicit links between generated images, human judgments, and physical-model inputs. This study presents an integrated human–artificial intelligence (AI) decision...
Blind image quality assessment (BIQA) without reference images remains significantly challenging due to the fact that perceptual quality is largely determined by subtle, spatially localized distortions. However, existing Contrastive Language–Im...
Wireless rechargeable sensor networks provide an effective solution to the energy limitation problem in wireless sensor networks by introducing chargers to recharge the nodes. On-demand charging algorithms, which schedule the mobile charger to charge...
Explicit ratio prompts can request intermediate writing styles, but endpoint classification does not reveal proportional responses at internal ratios. We present a geometric protocol using model-specific endpoints and shared references in external se...
Large language models (LLMs) can produce inaccurate answers even when relevant facts are supplied in the prompt. This study examines how graph data serialization, entity identifiers, and context selection affect factual question answering in knowledg...
This application was developed as part of a dissertation project, motivated by direct professional experience in the field of statistics and by the growing need to make statistical data more accessible in today’s data-driven context. Despite th...
of 4