Extended reality (XR) is well suited to support the situated learning of technical procedures. At the same time, AI-driven intelligent tutoring systems (ITS) can complement XR by providing adaptive pedagogical support. Many domains would benefit from this combination, especially when trainers, equipment, or team members are limited. We present a domain-agnostic XR-based ITS that integrates a training procedure representation (TPR), XR simulation, and an LLM-driven instructor. We demonstrate the tutor's use for tissue sample handling and engine repair, showing how it delivers adaptive feedback, collaborative roleplay, and dynamic scenario management to create realistic and pedagogically meaningful training experiences.

Abstract Designing optimal Network-on-Chip (NoC) architectures remains a complex challenge due to architectural intricacies and the high cost of simulation-based performance evaluation. This work presents NOCTOPUS, a novel framework that predicts optimal NoC configurations using System-on-Chip (SoC) parameters and performance metrics. At its core, NOCTOPUS is a pipelined Graph Neural Network (GNN) architecture, enhanced by human-in-the-loop learning to guide graph structure construction. A cycle-accurate NoC simulator generates a rich dataset via Latin Hypercube Sampling, enabling robust training and evaluation. Experimental results show that the proposed approach significantly outperforms traditional simulation methods in both accuracy and computational efficiency. Future directions include integrating deeper design knowledge and extending applicability to diverse SoC fabrics.

Social skills training targets behaviors necessary for success in social interactions. However, traditional classroom training for such skills is often insufficient to teach effective communication — one-to-one interaction in real-world scenarios is preferred to lecture-style information delivery. This paper introduces a framework that allows instructors to collaborate with large language models to dynamically design realistic scenarios for students to communicate. Our framework uses these scenarios to enable student rehearsal, provide immediate feedback and visualize performance for both students and instructors. Unlike traditional intelligent tutoring systems, instructors can easily co-create scenarios with a large language model without technical skills. Additionally, the system generates new scenario branches in real time when existing options don't fit the student's response.

Fine-grained bird sighting prediction is crucial for advancing ecological research, informing conservation planning, and enhancing the birdwatching experience while fostering public awareness of biodiversity. The rapid expansion of citizen-based bird observation networks has led to an exponential accumulation of bird sighting records, which can be leveraged to train machine learning models for more precise predictions. However, general-purpose machine learning models often fail to incorporate ecological factors that influence bird activity, resulting in less accurate predictions. In this paper, we present an ecologically informed machine learning framework based on LightGBM that integrates spatiotemporal correlations, ecological context, and dynamic environmental variables to improve bird sighting predictions. The framework captures temporal trends using rolling windows, applies spatial smoothing to account for observation proximity, and models ecological dependencies—such as temperature-food interactions—through interaction terms. Key environmental factors, including habitat classifications, weather conditions, and seasonally adjusted food availability proxies, are dynamically incorporated to enhance ecological relevance. Evaluation results demonstrate significant improvements in predictive accuracy, with increased F1-scores compared to baseline methods. By embedding ecological principles into machine learning models, this framework enables data-driven insights that reflect real-world environmental complexities, providing a powerful tool for biodiversity monitoring and conservation strategies.

Artificial intelligence (AI) and especially reinforcement learning (RL) have the potential to enable agents to learn and perform tasks autonomously with superhuman performance. However, we consider RL as fundamentally a Human-in-the-Loop (HITL) paradigm, even when an agent eventually performs its task autonomously. In cases where the reward function is challenging or impossible to define, HITL approaches are considered particularly advantageous. The application of Reinforcement Learning from Human Feedback (RLHF) in systems such as ChatGPT demonstrates the effectiveness of optimizing for user experience and integrating their feedback into the training loop. In HITL RL, human input is integrated during the agent’s learning process, allowing iterative updates and fine-tuning based on human feedback, thus enhancing the agent’s performance. Since the human is an essential part of this process, we argue that human-centric approaches are the key to successful RL, a fact that has not been adequately considered in the existing literature. This paper aims to inform readers about current explainability methods in HITL RL. It also shows how the application of explainable AI (xAI) and specific improvements to existing explainability approaches can enable a better human-agent interaction in HITL RL for all types of users, whether for lay people, domain experts, or machine learning specialists. Accounting for the workflow in HITL RL and based on software and machine learning methodologies, this article identifies four phases for human involvement for creating HITL RL systems: (1) Agent Development, (2) Agent Learning, (3) Agent Evaluation, and (4) Agent Deployment. We highlight human involvement, explanation requirements, new challenges, and goals for each phase. We furthermore identify low-risk, high-return opportunities for explainability research in HITL RL and present long-term research goals to advance the field. Finally, we propose a vision of human-robot collaboration that allows both parties to reach their full potential and cooperate effectively.

We propose an AI-based pilot trainer to help students learn how to fly aircraft. First, an AI agent uses behavioral cloning to learn flying maneuvers from qualified flight instructors. Later, the system uses the agent's decisions to detect errors made by students and provide feedback to help students correct their errors. This paper presents an instantiation of the pilot trainer. We focus on teaching straight and level flying maneuvers by automatically providing formative feedback to the human student.

We consider the problem of actively feature elicitation in which given a few examples with all the features (say the full EHR) and a few examples with some of the features (say demographics), the goal is to identify the set of examples on whom more information (say the lab tests) needs to be collected. The observation is that some set of features may be more expensive, personal or cumbersome to collect. We propose an active learning approach which identifies examples that are dissimilar to the ones with the full set of data and acquire the complete set of features for these examples. Motivated by real clinical tasks, our extensive evaluation on three clinical tasks demonstrate the effectiveness of this approach.

Major online messaging services such as Facebook Messenger and WhatsApp are starting to provide users with real-time information about when people read their messages, while useful, the feature has the potential to negatively impact privacy as well as cause concern over access to self. We report on two surveys using Mechanical Turk which looked at senders' (N=402} use of and reactions to the `message seen' feature, and recipients' (N=316) privacy and signaling behaviors in the face of such visibility. Our findings indicate that senders experience a range of emotions when their message is not read, or is read but not answered immediately. Recipients also engage in various signaling behaviors in the face of visibility by both replying or not replying immediately.

Social networking sites are starting to provide users with services that expose information about their audiences' composition and behavior, such as LinkedIn's 'Who's viewed my profile' feature. Providing information about content viewers to content publishers, however, raises new privacy concerns for viewers themselves, possibly creating a chilling effect on viewer behavior. We report on a study of 718 respondents using Mechanical Turk across two surveys to study publishers' (N=402) use and expectations of information about their viewers, and viewers' (N=316) privacy behaviors and concerns in the face of such visibility. Our findings indicate that publishers are generally mindful of viewers' privacy; viewers engage in various self-censorship behaviors in the face of visibility; and in some cases (e.g., dating sites) significant gender differences exist about what information respondents felt should be shared with publishers and required of viewers.