Large Language Models (LLMs) are increasingly deployed in roles requiring nuanced psychological understanding, such as emotional support agents, counselors, and decision-making assistants. However, their ability to interpret human personality traits, a critical aspect of such applications, remains unexplored, particularly in ecologically valid conversational settings. While prior work has simulated LLM "personas" using discrete Big Five labels on social media data, the alignment of LLMs with continuous, ground-truth personality assessments derived from natural interactions is largely unexamined. To address this gap, we introduce a novel benchmark comprising semi-structured interview transcripts paired with validated continuous Big Five trait scores. Using this dataset, we systematically evaluate LLM performance across three paradigms: (1) zero-shot and chain-of-thought prompting with GPT-4.1 Mini, (2) LoRA-based fine-tuning applied to both RoBERTa and Meta-LLaMA architectures, and (3) regression using static embeddings from pretrained BERT and OpenAI's text-embedding-3-small. Our results reveal that all Pearson correlations between model predictions and ground-truth personality traits remain below 0.26, highlighting the limited alignment of current LLMs with validated psychological constructs. Chain-of-thought prompting offers minimal gains over zero-shot, suggesting that personality inference relies more on latent semantic representation than explicit reasoning. These findings underscore the challenges of aligning LLMs with complex human attributes and motivate future work on trait-specific prompting, context-aware modeling, and alignment-oriented fine-tuning.

Object detection is a fundamental task in computer vision and image understanding, with the goal of identifying and localizing objects of interest within an image while assigning them corresponding class labels. Traditional methods, which relied on handcrafted features and shallow models, struggled with complex visual data and showed limited performance. These methods combined low-level features with contextual information and lacked the ability to capture high-level semantics. Deep learning, especially Convolutional Neural Networks (CNNs), addressed these limitations by automatically learning rich, hierarchical features directly from data. These features include both semantic and high-level representations essential for accurate object detection. This paper reviews object detection frameworks, starting with classical computer vision methods. We categorize object detection approaches into two groups: (1) classical computer vision techniques and (2) CNN-based detectors. We compare major CNN models, discussing their strengths and limitations. In conclusion, this review highlights the significant advancements in object detection through deep learning and identifies key areas for further research to improve performance.

Mental health disorders remain among the leading cause of disability worldwide, yet conditions such as depression, anxiety, and Post-Traumatic Stress Disorder (PTSD) are frequently underdiagnosed or misdiagnosed due to subjective assessments, limited clinical resources, and stigma and low awareness. In primary care settings, studies show that providers misidentify depression or anxiety in over 60% of cases, highlighting the urgent need for scalable, accessible, and context-aware diagnostic tools that can support early detection and intervention. In this study, we evaluate the effectiveness of machine learning models for mental health screening using a unique dataset of 553 real-world, semistructured interviews, each paried with ground-truth diagnoses for major depressive episodes (MDE), anxiety disorders, and PTSD. We benchmark multiple model classes, including zero-shot prompting with GPT-4.1 Mini and MetaLLaMA, as well as fine-tuned RoBERTa models using LowRank Adaptation (LoRA). Our models achieve over 80% accuracy across diagnostic categories, with especially strongperformance on PTSD (up to 89% accuracy and 98% recall). We also find that using shorter context, focused context segments improves recall, suggesting that focused narrative cues enhance detection sensitivity. LoRA fine-tuning proves both efficient and effective, with lower-rank configurations (e.g., rank 8 and 16) maintaining competitive performance across evaluation metrics. Our results demonstrate that LLM-based models can offer substantial improvements over traditional self-report screening tools, providing a path toward low-barrier, AI-powerd early diagnosis. This work lays the groundwork for integrating machine learning into real-world clinical workflows, particularly in low-resource or high-stigma environments where access to timely mental health care is most limited.

One can estimate the change of the Perron and Fiedler values for a connected network when the weight of an edge is perturbed by analyzing relevant entries of the Perron and Fiedler vectors. This is helpful for identifying edges whose weight perturbation causes the largest change in the Perron and Fiedler values. It also is important to investigate the sensitivity of the Perron and Fiedler vectors to perturbations. Applications of the perturbation analysis include the identification of edges that are critical for the structural robustness of the network.

This study explores the effectiveness of AI tools in enhancing student learning, specifically in improving study habits, time management, and feedback mechanisms. The research focuses on how AI tools can support personalized learning, adaptive test adjustments, and provide real-time classroom analysis. Student feedback revealed strong support for these features, and the study found a significant reduction in study hours alongside an increase in GPA, suggesting positive academic outcomes. Despite these benefits, challenges such as over-reliance on AI and difficulties in integrating AI with traditional teaching methods were also identified, emphasizing the need for AI tools to complement conventional educational strategies rather than replace them. Data were collected through a survey with a Likert scale and follow-up interviews, providing both quantitative and qualitative insights. The analysis involved descriptive statistics to summarize demographic data, AI usage patterns, and perceived effectiveness, as well as inferential statistics (T-tests, ANOVA) to examine the impact of demographic factors on AI adoption. Regression analysis identified predictors of AI adoption, and qualitative responses were thematically analyzed to understand students' perspectives on the future of AI in education. This mixed-methods approach provided a comprehensive view of AI's role in education and highlighted the importance of privacy, transparency, and continuous refinement of AI features to maximize their educational benefits.

Large Language Models (LLMs) are demonstrating remarkable human like capabilities across diverse domains, including psychological assessment. This study evaluates whether LLMs, specifically GPT-4o and GPT-4o mini, can infer Big Five personality traits and generate Big Five Inventory-10 (BFI-10) item scores from user conversations under zero-shot prompting conditions. Our findings reveal that incorporating an intermediate step--prompting for BFI-10 item scores before calculating traits--enhances accuracy and aligns more closely with the gold standard than direct trait inference. This structured approach underscores the importance of leveraging psychological frameworks in improving predictive precision. Additionally, a group comparison based on depressive symptom presence revealed differential model performance. Participants were categorized into two groups: those experiencing at least one depressive symptom and those without symptoms. GPT-4o mini demonstrated heightened sensitivity to depression-related shifts in traits such as Neuroticism and Conscientiousness within the symptom-present group, whereas GPT-4o exhibited strengths in nuanced interpretation across groups. These findings underscore the potential of LLMs to analyze real-world psychological data effectively, offering a valuable foundation for interdisciplinary research at the intersection of artificial intelligence and psychology.

As a promising paradigm to collaboratively train models with decentralized data, Federated Learning (FL) can be exploited to fine-tune Large Language Models (LLMs). While LLMs correspond to huge size, the scale of the training data significantly increases, which leads to tremendous amounts of computation and communication costs. The training data is generally non-Independent and Identically Distributed (non-IID), which requires adaptive data processing within each device. Although Low Rank Adaptation (LoRA) can significantly reduce the scale of parameters to update in the fine-tuning process, it still takes unaffordable time to transfer the low-rank parameters of all the layers in LLMs. In this paper, we propose a Fisher Information-based Efficient Curriculum Federated Learning framework (FibecFed) with two novel methods, i.e., adaptive federated curriculum learning and efficient sparse parameter update. First, we propose a fisher information-based method to adaptively sample data within each device to improve the effectiveness of the FL fine-tuning process. Second, we dynamically select the proper layers for global aggregation and sparse parameters for local update with LoRA so as to improve the efficiency of the FL fine-tuning process. Extensive experimental results based on 10 datasets demonstrate that FibecFed yields excellent performance (up to 45.35% in terms of accuracy) and superb fine-tuning speed (up to 98.61% faster) compared with 17 baseline approaches).

The nucleon exhibits a rich internal structure governed by Quantum Chromodynamics (QCD), where its electric charge arises from valence quarks, while its spin and mass emerge from complex interactions among valence quarks, sea (anti-)quarks, and gluons. At the advent of QCD, an alternative hypothesis emerged suggesting, at high energies, the transport of a nucleon's baryon number could be traced by a non-perturbative configuration of gluon fields connecting its three valence quarks, forming a $Y$-shaped topology known as the gluon junction. Recent measurements by the STAR experiment are compatible with this scenario. In light of these measurements, this study aims to explore the mechanisms of baryon transport in high-energy nuclear collisions using the PYTHIA-8 framework, which incorporates a state-of-the-art hadronization model with advanced Color Flow (CF) and Color Reconnection (CR) mechanisms which mimic signatures of a baryon junction. Within this model setup, we investigate (i) the rapidity slope of the net-baryon distributions in photon-included processes ($\gamma$+p) and (ii) baryon over charge transport in the isobaric (Ru+Ru and Zr+Zr) collisions. Our study highlights the importance of the CF and CR mechanisms in PYTHIA-8, which plays a crucial role in baryon transport. The results show that the CF and CR schemes significantly affect the isobaric baryon-to-charge ratio, leading to different predictions for baryon stopping and underscoring the need to account for CF and CR effects in comparisons with experimental measurements.

Accurate prediction of protein active site structures remains a central challenge in structural biology, particularly for short and flexible peptide fragments where conventional methods often fail. Here, we present a quantum computing framework specifically developed for utility-level quantum processors to address this problem. Starting from an amino acid sequence, we formulate the structure prediction task as a ground-state energy minimization problem using the Variational Quantum Eigensolver (VQE). Amino acid connectivity is encoded on a tetrahedral lattice model, and structural constraints-including steric, geometric, and chirality terms-are mapped into a problem-specific Hamiltonian expressed as sparse Pauli operators. The optimization is executed via a two-stage architecture separating energy estimation and measurement decoding, allowing noise mitigation under realistic quantum device conditions. We evaluate the framework on 23 randomly selected real protein fragments from the PDBbind dataset, as well as 7 real fragments from proteins with therapeutic potential, and run the experiments on the IBM-Cleveland Clinic quantum processor. Structural predictions are benchmarked against AlphaFold3 (AF3) using identical postprocessing and docking procedures. Our quantum method outperformed AF3 in both RMSD (Root-Mean-Square Deviation) and docking efficacy. This work demonstrates, for the first time, a complete end-to-end pipeline for biologically relevant structure prediction on real quantum hardware, highlighting its engineering feasibility and practical advantage over existing classical and deep learning approaches.

The construction industry increasingly relies on visual data to support Artificial Intelligence (AI) and Machine Learning (ML) applications for site monitoring. High-quality, domain-specific datasets, comprising images, videos, and point clouds, capture site geometry and spatiotemporal dynamics, including the location and interaction of objects, workers, and materials. However, despite growing interest in leveraging visual datasets, existing resources vary widely in sizes, data modalities, annotation quality, and representativeness of real-world construction conditions. A systematic review to categorize their data characteristics and application contexts is still lacking, limiting the community's ability to fully understand the dataset landscape, identify critical gaps, and guide future directions toward more effective, reliable, and scalable AI applications in construction. To address this gap, this study conducts an extensive search of academic databases and open-data platforms, yielding 51 publicly available visual datasets that span the 2005-2024 period. These datasets are categorized using a structured data schema covering (i) data fundamentals (e.g., size and license), (ii) data modalities (e.g., RGB and point cloud), (iii) annotation frameworks (e.g., bounding boxes), and (iv) downstream application domains (e.g., progress tracking). This study synthesizes these findings into an open-source catalog, OpenConstruction, supporting data-driven method development. Furthermore, the study discusses several critical limitations in the existing construction dataset landscape and presents a roadmap for future data infrastructure anchored in the Findability, Accessibility, Interoperability, and Reusability (FAIR) principles. By reviewing the current landscape and outlining strategic priorities, this study supports the advancement of data-centric solutions in the construction sector.

This paper investigates the use of Large Language Models (LLMs) to synthesize public opinion data, addressing challenges in traditional survey methods like declining response rates and non-response bias. We introduce a novel technique: role creation based on knowledge injection, a form of in-context learning that leverages RAG and specified personality profiles from the HEXACO model and demographic information, and uses that for dynamically generated prompts. This method allows LLMs to simulate diverse opinions more accurately than existing prompt engineering approaches. We compare our results with pre-trained models with standard few-shot prompts. Experiments using questions from the Cooperative Election Study (CES) demonstrate that our role-creation approach significantly improves the alignment of LLM-generated opinions with real-world human survey responses, increasing answer adherence. In addition, we discuss challenges, limitations and future research directions.

In this paper, we perform a systemic examination of the recommendation losses, including listwise (softmax), pairwise(BPR), and pointwise (mean-squared error, MSE, and Cosine Contrastive Loss, CCL) losses through the lens of contrastive learning. We introduce and study both debiased InfoNCE and mutual information neural estimator (MINE), for the first time, under the recommendation setting. We also relate and differentiate these two losses with the BPR loss through the lower bound analysis. Furthermore, we present the debiased pointwise loss (for both MSE and CCL) and theoretically certify both iALS and EASE, two of the most popular linear models, are inherently debiased. The empirical experimental results demonstrate the effectiveness of the debiased losses and newly introduced mutual-information losses outperform the existing (biased) ones.

In this work, we defined an attack vector for networks utilizing the Internet of Medical Things (IoMT) devices and compute the probability distribution of IoMT security threats based on Markov chain and Common Vulnerability Scoring System (CVSS). IoMT is an emerging technology that improves patients' quality of life by permitting personalized e-health services without restrictions on time and site. The IoMT consists of embedded objects, sensors, and actuators that transmit and receive medical data. These Medical devices are vulnerable to different types of security threats, and thus, they pose a significant risk to patient's privacy and safety. Because security is a critical factor for successfully merging IoMT into pervasive healthcare systems, there is an urgent need for new security mechanisms to prevent threats on the IoMT edge network. Toward this direction, the first step is defining an attack vector that an attacker or unauthorized user can take advantage of to penetrate and tamper with medical data. In this article, we specify a threat model for the IoMT edge network. We identify any vulnerabilities or weaknesses within the IoMT network that allow unauthorized privileges and threats that can utilize these weaknesses to compromise the IoMT edge network. Finally, we compute the probability distribution of IoMT threats based on the Markov transition probability matrix.