Cultural competence, defined as the ability to understand and adapt to multicultural contexts, is increasingly vital for large language models (LLMs) in global environments. While several cultural benchmarks exist to assess LLMs' cultural competence, current evaluations suffer from fragmented taxonomies, domain specificity, and heavy reliance on manual data annotation. To address these limitations, we introduce CultureSynth, a novel framework comprising (1) a comprehensive hierarchical multilingual cultural taxonomy covering 12 primary and 130 secondary topics, and (2) a Retrieval-Augmented Generation (RAG)-based methodology leveraging factual knowledge to synthesize culturally relevant question-answer pairs. The CultureSynth-7 synthetic benchmark contains 19,360 entries and 4,149 manually verified entries across 7 languages. Evaluation of 14 prevalent LLMs of different sizes reveals clear performance stratification led by ChatGPT-4o-Latest and Qwen2.5-72B-Instruct. The results demonstrate that a 3B-parameter threshold is necessary for achieving basic cultural competence, models display varying architectural biases in knowledge processing, and significant geographic disparities exist across models. We believe that CultureSynth offers a scalable framework for developing culturally aware AI systems while reducing reliance on manual annotation\footnote{Benchmark is available at https://github.com/Eyr3/CultureSynth.}.

Transfer learning is commonly utilized in various fields such as computer vision, natural language processing, and medical imaging due to its impressive capability to address subtasks and work with different datasets. However, its application in cybersecurity has not been thoroughly explored. In this paper, we present an innovative neurosymbolic AI framework designed for network intrusion detection systems, which play a crucial role in combating malicious activities in cybersecurity. Our framework leverages transfer learning and uncertainty quantification. The findings indicate that transfer learning models, trained on large and well-structured datasets, outperform neural-based models that rely on smaller datasets, paving the way for a new era in cybersecurity solutions.

Large Language Models (LLMs) exhibit impressive reasoning and question-answering capabilities. However, they often produce inaccurate or unreliable content known as hallucinations. This unreliability significantly limits their deployment in high-stakes applications. Thus, there is a growing need for a general-purpose method to detect hallucinations in LLMs. In this work, we introduce HalluField, a novel field-theoretic approach for hallucination detection based on a parametrized variational principle and thermodynamics. Inspired by thermodynamics, HalluField models an LLM's response to a given query and temperature setting as a collection of discrete likelihood token paths, each associated with a corresponding energy and entropy. By analyzing how energy and entropy distributions vary across token paths under changes in temperature and likelihood, HalluField quantifies the semantic stability of a response. Hallucinations are then detected by identifying unstable or erratic behavior in this energy landscape. HalluField is computationally efficient and highly practical: it operates directly on the model's output logits without requiring fine-tuning or auxiliary neural networks. Notably, the method is grounded in a principled physical interpretation, drawing analogies to the first law of thermodynamics. Remarkably, by modeling LLM behavior through this physical lens, HalluField achieves state-of-the-art hallucination detection performance across models and datasets.

Despite the widespread adoption of endoscopic devices for several cancer screening procedures, manual control of these devices still remains challenging for clinicians, leading to several critical issues such as increased workload, fatigue, and distractions. To address these issues, in this paper, we introduce the design and development of an intuitive, modular, and easily installable mechatronic framework. This framework includes (i) a novel nested collet-chuck gripping mechanism that can readily be integrated and assembled with the existing endoscopic devices and control their bending degrees-of-freedom (DoFs); (ii) a feeder mechanism that can control the insertion/retraction DoF of a colonoscope, and (iii) a complementary and intuitive user interface that enables simultaneous control of all DoFs during the procedure. To analyze the design of the proposed mechanisms, we also introduce a mathematical modeling approach and a design space for optimal selection of the parameters involved in the design of gripping and feeder mechanisms. Our simulation and experimental studies thoroughly demonstrate the performance of the proposed mathematical modeling and robotic framework.

The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios. Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action. Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots. Human oversight improved avoidance but introduced costs such as attentional tunneling and cognitive load. Our findings show neither humans nor agents are uniformly resilient, and collaboration introduces new vulnerabilities, suggesting design needs for transparency, adjustable autonomy, and oversight.

Sequential fine-tuning of transformers is useful when new data arrive sequentially, especially with shifting distributions. Unlike batch learning, sequential learning demands that training be stabilized despite a small amount of data by balancing new information and previously learned knowledge in the pre-trained models. This challenge is further complicated when training is to be completed in latency-critical environments and learning must additionally quantify and be mediated by uncertainty. Motivated by these challenges, we propose a novel method that frames sequential fine-tuning as a posterior inference problem within a Bayesian framework. Our approach integrates closed-form moment propagation of random variables, Kalman Bayesian Neural Networks, and Taylor approximations of the moments of softmax functions. By explicitly accounting for pre-trained models as priors and adaptively balancing them against new information based on quantified uncertainty, our method achieves robust and data-efficient sequential learning. The effectiveness of our method is demonstrated through numerical simulations involving sequential adaptation of a decision transformer to tasks characterized by distribution shifts and limited memory resources.

This paper presents a novel approach to motion planning and risk analysis for enhancing human-robot collaboration using a Multi-Rotor Aerial Vehicle (MRAV). The proposed method uses Signal Temporal Logic (STL) to encode key mission objectives, such as safety, timing, and human preferences, with a strong focus on ergonomics and comfort. An optimization framework generates dynamically feasible trajectories while considering the MRAV's physical constraints. Given the nonlinear and non-convex nature of the problem, smooth approximations and gradient-based techniques assist in handling the problem's computational complexity. Additionally, an uncertainty-aware risk analysis is incorporated to assess potential deviations from the mission specifications, providing insights into the likelihood of mission success under uncertain conditions. Further, an event-triggered replanning strategy is implemented to respond to unforeseen events and external disturbances. The approach is validated through MATLAB and Gazebo simulations, using an object handover task in a mock-up environment inspired by power line maintenance scenarios. The results highlight the method's effectiveness in achieving safe, efficient, and resilient human-robot collaboration.

The success and wide adoption of generative AI (GenAI), particularly large language models (LLMs), has attracted the attention of cybercriminals seeking to abuse models, steal sensitive data, or disrupt services. Moreover, providing security to LLM-based systems is a great challenge, as both traditional threats to software applications and threats targeting LLMs and their integration must be mitigated. In this survey, we shed light on security and privacy concerns of such LLM-based systems by performing a systematic review and comprehensive categorization of threats and defensive strategies considering the entire software and LLM life cycles. We analyze real-world scenarios with distinct characteristics of LLM usage, spanning from development to operation. In addition, threats are classified according to their severity level and to which scenarios they pertain, facilitating the identification of the most relevant threats. Recommended defense strategies are systematically categorized and mapped to the corresponding life cycle phase and possible attack strategies they attenuate. This work paves the way for consumers and vendors to understand and efficiently mitigate risks during integration of LLMs in their respective solutions or organizations. It also enables the research community to benefit from the discussion of open challenges and edge cases that may hinder the secure and privacy-preserving adoption of LLM-based systems.

AI-driven digital ecosystems span diverse stakeholders including technology firms, regulators, accelerators and civil society, yet often lack cohesive ethical governance. This paper proposes a four-pillar framework (SCOR) to embed accountability, fairness, and inclusivity across such multi-actor networks. Leveraging a design science approach, we develop a Shared Ethical Charter(S), structured Co-Design and Stakeholder Engagement protocols(C), a system of Continuous Oversight and Learning(O), and Adaptive Regulatory Alignment strategies(R). Each component includes practical guidance, from lite modules for resource-constrained start-ups to in-depth auditing systems for larger consortia. Through illustrative vignettes in healthcare, finance, and smart city contexts, we demonstrate how the framework can harmonize organizational culture, leadership incentives, and cross-jurisdictional compliance. Our mixed-method KPI design further ensures that quantitative targets are complemented by qualitative assessments of user trust and cultural change. By uniting ethical principles with scalable operational structures, this paper offers a replicable pathway toward responsible AI innovation in complex digital ecosystems.

Large Language Models (LLMs) are increasingly integrated into financial applications, yet existing red-teaming research primarily targets harmful content, largely neglecting regulatory risks. In this work, we aim to investigate the vulnerability of financial LLMs through red-teaming approaches. We introduce Risk-Concealment Attacks (RCA), a novel multi-turn framework that iteratively conceals regulatory risks to provoke seemingly compliant yet regulatory-violating responses from LLMs. To enable systematic evaluation, we construct FIN-Bench, a domain-specific benchmark for assessing LLM safety in financial contexts. Extensive experiments on FIN-Bench demonstrate that RCA effectively bypasses nine mainstream LLMs, achieving an average attack success rate (ASR) of 93.18%, including 98.28% on GPT-4.1 and 97.56% on OpenAI o1. These findings reveal a critical gap in current alignment techniques and underscore the urgent need for stronger moderation mechanisms in financial domains. We hope this work offers practical insights for advancing robust and domain-aware LLM alignment.