Large language models (LLMs) show promise for diagnostic reasoning but often lack reliable, knowledge grounded inference. Knowledge graphs (KGs), such as the Unified Medical Language System (UMLS), offer structured biomedical knowledge that can support trustworthy reasoning. Prior approaches typically integrate KGs via retrieval augmented generation or fine tuning, inserting KG content into prompts rather than enabling structured reasoning. We explore an alternative paradigm: treating the LLM as a reward model of KG reasoning paths, where the model learns to judge whether a candidate path leads to correct diagnosis for a given patient input. This approach is inspired by recent work that leverages reward training to enhance model reasoning abilities, and grounded in computational theory, which suggests that verifying a solution is often easier than generating one from scratch. It also parallels physicians' diagnostic assessment, where they judge which sequences of findings and intermediate conditions most plausibly support a diagnosis. We first systematically evaluate five task formulation for knowledge path judging and eight training paradigm. Second, we test whether the path judging abilities generalize to downstream diagnostic tasks, including diagnosis summarization and medical question answering. Experiments with three open source instruct-tuned LLMs reveal both promise and brittleness: while specific reward optimization and distillation lead to strong path-judging performance, the transferability to downstream tasks remain weak. Our finding provides the first systematic assessment of "reward model style" reasoning over clinical KGs, offering insights into how structured, reward-based supervision influences diagnostic reasoning in GenAI systems for healthcare.

We propose a framework for online Change Point Detection (CPD) from multi-entity, multivariate time series data, motivated by applications in crowd monitoring where traditional sensing methods (e.g., video surveillance) may be infeasible. Our approach addresses the challenge of detecting system-wide behavioral shifts in complex, dynamic environments where the number and behavior of individual entities may be uncertain or evolve. We introduce the concept of Individual Deviation from Normality (IDfN), computed via a reconstruction-error-based autoencoder trained on normal behavior. We aggregate these individual deviations using mean, variance, and Kernel Density Estimates (KDE) to yield a System-Wide Anomaly Score (SWAS). To detect persistent or abrupt changes, we apply statistical deviation metrics and the Cumulative Sum (CUSUM) technique to these scores. Our unsupervised approach eliminates the need for labeled data or feature extraction, enabling real-time operation on streaming input. Evaluations on both synthetic datasets and crowd simulations, explicitly designed for anomaly detection in group behaviors, demonstrate that our method accurately detects significant system-level changes, offering a scalable and privacy-preserving solution for monitoring complex multi-agent systems. In addition to this methodological contribution, we introduce new, challenging multi-entity multivariate time series datasets generated from crowd simulations in Unity and coupled nonlinear oscillators. To the best of our knowledge, there is currently no publicly available dataset of this type designed explicitly to evaluate CPD in complex collective and interactive systems, highlighting an essential gap that our work addresses.

Even though current generation of AI is underpinned by a common technology - namely machine learning, especially in the form of deep learning - in the public eye it has not emerged as a single solution. Rather, it has taken shape through multiple and overlapping applications - ranging from predictive diagnostics in healthcare and algorithmic hiring systems in HR to autonomous weapons and generative language models. As AI becomes increasingly embedded in sector - specific infrastructures, the question of how publics perceive its us e is gaining urgency. Existing literature on public perception of AI suggests that attitudes are highly sensitive to the application domain . People tend to be more supportive of AI in domains where it is perceived to augment human capacity (e.g., in medical diagnostics) and more sceptical when AI is seen as replacing judg e ment or threatening civil liberties or rights (e.g., in security or surveillance). These perceptions are shaped not only by technical features of the AI system but also by institutional trust, cultural attitude s toward risk, and the moral economy of the domain in question. Despite this, few reviews have systematically compared public perceptions across sectors and explored the cross - domain patterns and differences in attitudes.

Knowledge Tracing (KT) plays a central role in assessing students' skill mastery and predicting their future performance. While deep learning-based KT models achieve superior predictive accuracy compared to traditional methods, their complexity and opacity hinder their ability to provide psychologically meaningful explanations. This disconnect between model parameters and cognitive theory poses challenges for understanding and enhancing the learning process, limiting their trustworthiness in educational applications. To address these challenges, we enhance interpretable KT models by exploring human-understandable features derived from students' interaction data. By incorporating additional features, particularly those reflecting students' learning abilities, our enhanced approach improves predictive accuracy while maintaining alignment with cognitive theory. Our contributions aim to balance predictive power with interpretability, advancing the utility of adaptive learning systems.

Controlling desktop applications via software remains a fundamental yet under-served problem. Existing multi-modal large language models (MLLMs) ingest screenshots and task instructions to generate keystrokes and mouse events, but they suffer from prohibitive inference latency, poor sample efficiency on long-horizon sparse-reward tasks, and infeasible on-device deployment. We introduce a lightweight hierarchical reinforcement learning framework, ComputerAgent, that formulates OS control as a two-level option process (manager and subpolicy), employs a triple-modal state encoder (screenshot, task ID, numeric state) to handle visual and contextual diversity, integrates meta-actions with an early-stop mechanism to reduce wasted interactions, and uses a compact vision backbone plus small policy networks for on-device inference (15M parameters). On a suite of 135 real-world desktop tasks, ComputerAgent attains 92.1% success on simple tasks (<8 steps) and 58.8% on hard tasks (>=8 steps), matching or exceeding 200B-parameter MLLM baselines on simple scenarios while reducing model size by over four orders of magnitude and halving inference time. These results demonstrate that hierarchical RL offers a practical, scalable alternative to monolithic MLLM-based automation for computer control.

Generative AI, and specifically GPT, can produce a remarkable solution to a mechanical engineering analysis problem - but also, on occasion, a flawed solution. For example, an elementary mechanics problem is solved flawlessly in one GPT instance and incorrectly in a subsequent GPT instance, with a success probability of only 85%. This unreliability renders "out-of-the-box" GPT unsuitable for deployment in education or engineering practice. We introduce an "N-Plus-1" GPT Agency for Initial (Low-Cost) Analysis of mechanical engineering Problem Statements. Agency first launches N instantiations of Agent Solve to yield N independent Proposed Problem Solution Realizations; Agency then invokes Agent Compare to summarize and compare the N Proposed Problem Solution Realizations and to provide a Recommended Problem Solution. We argue from Condorcet's Jury Theorem that, for a Problem Statement characterized by per-Solve success probability greater than 1/2 (and N sufficiently large), the Predominant (Agent Compare) Proposed Problem Solution will, with high probability, correspond to a Correct Proposed Problem Solution. Furthermore, Agent Compare can also incorporate aspects of Secondary (Agent Compare) Proposed Problem Solutions, in particular when the latter represent alternative Problem Statement interpretations - different Mathematical Models - or alternative Mathematical Solution Procedures. Comparisons to Grok Heavy, a commercial multi-agent model, show similarities in design and performance, but also important differences in emphasis: our Agency focuses on transparency and pedagogical value.

Personalized recipe recommendation faces challenges in handling fuzzy user intent, ensuring semantic accuracy, and providing sufficient detail coverage. We propose ChefMind, a hybrid architecture combining Chain of Exploration (CoE), Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and a Large Language Model (LLM). CoE refines ambiguous queries into structured conditions, KG offers semantic reasoning and interpretability, RAG supplements contextual culinary details, and LLM integrates outputs into coherent recommendations. We evaluate ChefMind on the Xiachufang dataset and manually annotated queries, comparing it with LLM-only, KG-only, and RAG-only baselines. Results show that ChefMind achieves superior performance in accuracy, relevance, completeness, and clarity, with an average score of 8.7 versus 6.4-6.7 for ablation models. Moreover, it reduces unprocessed queries to 1.6%, demonstrating robustness in handling fuzzy demands.

With the rising global burden of chronic diseases and the multimodal and heterogeneous clinical data (medical imaging, free-text recordings, wearable sensor streams, etc.), there is an urgent need for a unified multimodal AI framework that can proactively predict individual health risks. We propose VL-RiskFormer, a hierarchical stacked visual-language multimodal Transformer with a large language model (LLM) inference head embedded in its top layer. The system builds on the dual-stream architecture of existing visual-linguistic models (e.g., PaLM-E, LLaVA) with four key innovations: (i) pre-training with cross-modal comparison and fine-grained alignment of radiological images, fundus maps, and wearable device photos with corresponding clinical narratives using momentum update encoders and debiased InfoNCE losses; (ii) a time fusion block that integrates irregular visit sequences into the causal Transformer decoder through adaptive time interval position coding; (iii) a disease ontology map adapter that injects ICD-10 codes into visual and textual channels in layers and infers comorbid patterns with the help of a graph attention mechanism. On the MIMIC-IV longitudinal cohort, VL-RiskFormer achieved an average AUROC of 0.90 with an expected calibration error of 2.7 percent.

In this study, we classify the magnetic chirality of solar filaments from H-Alpha observations using state-of-the-art image classification models. We establish the first reproducible baseline for solar filament chirality classification on the MAGFiLO dataset. The MAGFiLO dataset contains over 10,000 manually-annotated filaments from GONG H-Alpha observations, making it the largest dataset for filament detection and classification to date. Prior studies relied on much smaller datasets, which limited their generalizability and comparability. We fine-tuned several pre-trained, image classification architectures, including ResNet, WideResNet, ResNeXt, and ConvNeXt, and also applied data augmentation and per-class loss weights to optimize the models. Our best model, ConvNeXtBase, achieves a per-class accuracy of 0.69 for left chirality filaments and $0.73$ for right chirality filaments.

Task vectors capture how a model changes during fine-tuning by recording the difference between pre-trained and task-specific weights. The composition of task vectors, a key operator in task arithmetic, enables models to integrate knowledge from multiple tasks without incurring additional inference costs. In this paper, we propose variational task vector composition, where composition coefficients are taken as latent variables and estimated in a Bayesian inference framework. Unlike previous methods that operate at the task level, our framework focuses on sample-specific composition. Motivated by the observation of structural redundancy in task vectors, we introduce a Spike-and-Slab prior that promotes sparsity and preserves only the most informative components. To further address the high variance and sampling inefficiency in sparse, high-dimensional spaces, we develop a gated sampling mechanism that constructs a controllable posterior by filtering the composition coefficients based on both uncertainty and importance. This yields a more stable and interpretable variational framework by deterministically selecting reliable task components, reducing sampling variance while improving transparency and generalization. Experimental results demonstrate that our method consistently outperforms existing approaches across all datasets by selectively leveraging the most reliable and informative components in task vectors. These findings highlight the practical value of our approach, establishing a new standard for efficient and effective task vector composition.