Abstract
Nowadays, eXtended Reality (XR) has matured to the point where it seamlessly integrates various input and output modalities, enhancing the way users interact with digital environments. From traditional controllers and hand tracking to voice commands, eye tracking, and even biometric sensors, XR systems now offer more natural interactions. Similarly, output modalities have expanded beyond visual displays to include haptic feedback, spatial audio, and others, enriching the overall user experience. In this vein, as the field of XR becomes increasingly multimodal, the education process must also evolve to reflect these advancements. There is a growing need to incorporate additional modalities into the curriculum, helping students understand their relevance and practical applications. By exposing students to a diverse range of interaction techniques, they can better assess which modalities are most suitable for different contexts, enabling them to design more effective and human-centered solutions. This work describes an Advanced Human-Machine Interaction (HMI) course aimed at Doctoral Students in Computer Science. The primary objective is to provide students with the necessary knowledge in HMI by enabling them to articulate the fundamental concepts of the field, recognize and analyze the role of human factors, identify modern interaction methods and technologies, apply HCD principles to interactive system design and development, and implement appropriate methods for assessing interaction experiences across advanced HMI topics. In this vein, the course structure, the range of topics covered, assessment strategies, as well as the hardware and infrastructure employed are presented. Additionally, it highlights mini-projects, including flexibility for students to integrate their projects, fostering personalized and project-driven learning. The discussion reflects on the challenges inherent in keeping pace with this rapidly evolving field and emphasizes the importance of adapting to emerging trends. Finally, the paper outlines future directions and potential enhancements for the course.

Abstract
The growing reliance on e-commerce and the demand for efficient intralogistics operations have increased the need for automation, while labour shortages continue to pose significant challenges. When combined with the inherent risks of forklift operation, this circumstance prompted businesses to look for robotic solutions for intralogistics tasks. However, robots are still limited when they come across situations that are outside of their programming scope and often need assistance from humans. To achieve the long-term goal of enhancing intralogistics operation, we propose the development of a virtual reality-based teleoperation system that allows remote operation of robot forklifts with minimal latency. Considering the specificities of the teleoperation process and network dynamics, we conduct detailed modelling to analyse latency factors, optimise system performance, and ensure a seamless user experience. Experimental results on a mobile robot have shown that the proposed teleoperation system achieves an average glass-to-glass latency of 368 ms, with capturing latency contributing to approximately 60% of the total delay. The results also indicate that network oscillations significantly impact image quality and user experience, emphasising the importance of a stable network infrastructure.

Abstract
Hyperparameter optimization (HPO) is critical for enhancing the predictive performance of machine learning models in credit risk assessment for peer-to-peer (P2P) lending. This study evaluates four HPO methods, Grid Search, Random Search, Hyperopt, and Optuna, across four models, Logistic Regression, Random Forest, XGBoost, and LightGBM, using three real-world datasets (Lending Club, Australia, Taiwan). We assess predictive accuracy (AUC, Sensitivity, Specificity, G-Mean), computational efficiency, robustness, and interpretability. LightGBM achieves the highest AUC (e.g., 70.77% on Lending Club, 93.25% on Australia, 77.85% on Taiwan), with XGBoost performing comparably. Bayesian methods (Hyperopt, Optuna) match or approach Grid Search's accuracy while reducing runtime by up to 75.7-fold (e.g., 3.19 vs. 241.47 min for LightGBM on Lending Club). A sensitivity analysis confirms robust hyperparameter configurations, with AUC variations typically below 0.4% under +/- 10% perturbations. A feature importance analysis, using gain and SHAP metrics, identifies debt-to-income ratio and employment title as key default predictors, with stable rankings (Spearman correlation > 0.95, p<0.01) across tuning methods, enhancing model interpretability. Operational impact depends on data quality, scalable infrastructure, fairness audits for features like employment title, and stakeholder collaboration to ensure compliance with regulations like the EU AI Act and U.S. Equal Credit Opportunity Act. These findings advocate Bayesian HPO and ensemble models in P2P lending, offering scalable, transparent, and fair solutions for default prediction, with future research suggested to explore advanced resampling, cost-sensitive metrics, and feature interactions.

Abstract
This paper presents a semantic characterization of leakage-freeness through timing side-channels for Jasmin programs. Our characterization covers probabilistic Jasmin programs that are not constant-time. In addition, we provide a characterization in terms of probabilistic relational Hoare logic and prove the equivalence between both definitions. We also prove that our new characterizations are compositional and relate our new definitions to existing ones from prior work, which could only be applied to deterministic programs. To provide practical evidence, we use the Jasmin framework to develop a rejection sampling algorithm and provide an EasyCrypt proof that ensures the algorithm's implementation is leakage-free while not being constant-time.

Abstract

Abstract
Abstract This paper investigates the ability of large language models (LLMs) to evaluate semantic relations between word pairs by examining their alignment with human-generated semantic ratings. Semantic relations represent the degree of connection (e.g., relatedness or similarity) between linguistic elements and are traditionally validated against human-annotated datasets. Due to the challenges of building such datasets and recent progress in LLMs’ capacity to model human-like understanding, we explore whether LLMs can serve as reliable substitutes for traditional human ratings. We conducted experiments using multiple LLMs from OpenAI, Google, Mistral, and Anthropic, evaluating their performance across diverse English and Portuguese semantic relations datasets. We included in the analysis PAP900, a recently published dataset of semantic relations in Portuguese, to examine the influence of prior exposure to the dataset on LLM training. The results show that the LLM predictions correlate strongly with human ratings. The findings reveal the potential of LLMs to supplement or replace traditional semantic measure algorithms and crowd-sourced human annotations in semantic tasks.