arXiv subjects

Enkelejda Kasneci

Publications and source records attributed to Enkelejda Kasneci.

At least 55 records · Page 3Linked to original sources

arXiv2025

User Identification with LFI-Based Eye Movement Data Using Time and Frequency Domain Features

Laser interferometry (LFI)-based eye-tracking systems provide an alternative to traditional camera-based solutions, offering improved privacy by eliminating the risk of direct visual identification. However, the high-frequency signals captured by LFI-based trackers may still contain biometric information that enables user identification. This study investigates user identification from raw high-frequency LFI-based eye movement data by analyzing features extracted from both the time and frequency domains. Using velocity and distance measurements without requiring direct gaze data, we develop a multi-class classification model to accurately distinguish between individuals across various activities. Our results demonstrate that even without direct visual cues, eye movement patterns exhibit sufficient uniqueness for user identification, achieving 93.14% accuracy and a 2.52% EER with 5-second windows across both static and dynamic tasks. Additionally, we analyze the impact of sampling rate and window size on model performance, providing insights into the feasibility of LFI-based biometric recognition. Our findings demonstrate the novel potential of LFI-based eye-tracking for user identification, highlighting both its promise for secure authentication and emerging privacy risks. This work paves the way for further research into high-frequency eye movement data.

cs.HC↗

arXiv2025

Examining the Role of LLM-Driven Interactions on Attention and Cognitive Engagement in Virtual Classrooms

Transforming educational technologies through the integration of large language models (LLMs) and virtual reality (VR) offers the potential for immersive and interactive learning experiences. However, the effects of LLMs on user engagement and attention in educational environments remain open questions. In this study, we utilized a fully LLM-driven virtual learning environment, where peers and teachers were LLM-driven, to examine how students behaved in such settings. Specifically, we investigate how peer question-asking behaviors influenced student engagement, attention, cognitive load, and learning outcomes and found that, in conditions where LLM-driven peer learners asked questions, students exhibited more targeted visual scanpaths, with their attention directed toward the learning content, particularly in complex subjects. Our results suggest that peer questions did not introduce extraneous cognitive load directly, as the cognitive load is strongly correlated with increased attention to the learning material. Considering these findings, we provide design recommendations for optimizing VR learning spaces.

cs.HC↗

arXiv2025

Multimodal Assessment of Classroom Discourse Quality: A Text-Centered Attention-Based Multi-Task Learning Approach

Classroom discourse is an essential vehicle through which teaching and learning take place. Assessing different characteristics of discursive practices and linking them to student learning achievement enhances the understanding of teaching quality. Traditional assessments rely on manual coding of classroom observation protocols, which is time-consuming and costly. Despite many studies utilizing AI techniques to analyze classroom discourse at the utterance level, investigations into the evaluation of discursive practices throughout an entire lesson segment remain limited. To address this gap, our study proposes a novel text-centered multimodal fusion architecture to assess the quality of three discourse components grounded in the Global Teaching InSights (GTI) observation protocol: Nature of Discourse, Questioning, and Explanations. First, we employ attention mechanisms to capture inter- and intra-modal interactions from transcript, audio, and video streams. Second, a multi-task learning approach is adopted to jointly predict the quality scores of the three components. Third, we formulate the task as an ordinal classification problem to account for rating level order. The effectiveness of these designed elements is demonstrated through an ablation study on the GTI Germany dataset containing 92 videotaped math lessons. Our results highlight the dominant role of text modality in approaching this task. Integrating acoustic features enhances the model's consistency with human ratings, achieving an overall Quadratic Weighted Kappa score of 0.384, comparable to human inter-rater reliability (0.326). Our study lays the groundwork for the future development of automated discourse quality assessment to support teacher professional development through timely feedback on multidimensional discourse practices.

cs.CY↗

arXiv2025

Adaptive Gen-AI Guidance in Virtual Reality: A Multimodal Exploration of Engagement in Neapolitan Pizza-Making

Virtual reality (VR) offers promising opportunities for procedural learning, particularly in preserving intangible cultural heritage. Advances in generative artificial intelligence (Gen-AI) further enrich these experiences by enabling adaptive learning pathways. However, evaluating such adaptive systems using traditional temporal metrics remains challenging due to the inherent variability in Gen-AI response times. To address this, our study employs multimodal behavioural metrics, including visual attention, physical exploratory behaviour, and verbal interaction, to assess user engagement in an adaptive VR environment. In a controlled experiment with 54 participants, we compared three levels of adaptivity (high, moderate, and non-adaptive baseline) within a Neapolitan pizza-making VR experience. Results show that moderate adaptivity optimally enhances user engagement, significantly reducing unnecessary exploratory behaviour and increasing focused visual attention on the AI avatar. Our findings suggest that a balanced level of adaptive AI provides the most effective user support, offering practical design recommendations for future adaptive educational technologies.

cs.HC↗

arXiv2025

LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images

Deep learning has bolstered gaze estimation techniques, but real-world deployment has been impeded by inadequate training datasets. This problem is exacerbated by both hardware-induced variations in eye images and inherent biological differences across the recorded participants, leading to both feature and pixel-level variance that hinders the generalizability of models trained on specific datasets. While synthetic datasets can be a solution, their creation is both time and resource-intensive. To address this problem, we present a framework called Light Eyes or "LEyes" which, unlike conventional photorealistic methods, only models key image features required for video-based eye tracking using simple light distributions. LEyes facilitates easy configuration for training neural networks across diverse gaze-estimation tasks. We demonstrate that models trained using LEyes are consistently on-par or outperform other state-of-the-art algorithms in terms of pupil and CR localization across well-known datasets. In addition, a LEyes trained model outperforms the industry standard eye tracker using significantly more cost-effective hardware. Going forward, we are confident that LEyes will revolutionize synthetic data generation for gaze estimation models, and lead to significant improvements of the next generation video-based eye trackers.

cs.CV↗

arXiv2025

TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients

Federated learning is a distributed collaborative machine learning paradigm that has gained strong momentum in recent years. In federated learning, a central server periodically coordinates models with clients and aggregates the models trained locally by clients without necessitating access to local data. Despite its potential, the implementation of federated learning continues to encounter several challenges, predominantly the slow convergence that is largely due to data heterogeneity. The slow convergence becomes particularly problematic in cross-device federated learning scenarios where clients may be strongly limited by computing power and storage space, and hence counteracting methods that induce additional computation or memory cost on the client side such as auxiliary objective terms and larger training iterations can be impractical. In this paper, we propose a novel federated aggregation strategy, TurboSVM-FL, that poses no additional computation burden on the client side and can significantly accelerate convergence for federated classification task, especially when clients are "lazy" and train their models solely for few epochs for next global aggregation. TurboSVM-FL extensively utilizes support vector machine to conduct selective aggregation and max-margin spread-out regularization on class embeddings. We evaluate TurboSVM-FL on multiple datasets including FEMNIST, CelebA, and Shakespeare using user-independent validation with non-iid data distribution. Our results show that TurboSVM-FL can significantly outperform existing popular algorithms on convergence rate and reduce communication rounds while delivering better test metrics including accuracy, F1 score, and MCC.

cs.LG↗

arXiv2025

Trade-offs in Privacy-Preserving Eye Tracking through Iris Obfuscation: A Benchmarking Study

Recent developments in hardware, computer graphics, and AI may soon enable AR/VR head-mounted displays (HMDs) to become everyday devices like smartphones and tablets. Eye trackers within HMDs provide a special opportunity for such setups as it is possible to facilitate gaze-based research and interaction. However, estimating users' gaze information often requires raw eye images and videos that contain iris textures, which are considered a gold standard biometric for user authentication, and this raises privacy concerns. Previous research in the eye-tracking community focused on obfuscating iris textures while keeping utility tasks such as gaze estimation accurate. Despite these attempts, there is no comprehensive benchmark that evaluates state-of-the-art approaches. Considering all, in this paper, we benchmark blurring, noising, downsampling, rubber sheet model, and iris style transfer to obfuscate user identity, and compare their impact on image quality, privacy, utility, and risk of imposter attack on two datasets. We use eye segmentation and gaze estimation as utility tasks, and reduction in iris recognition accuracy as a measure of privacy protection, and false acceptance rate to estimate risk of attack. Our experiments show that canonical image processing methods like blurring and noising cause a marginal impact on deep learning-based tasks. While downsampling, rubber sheet model, and iris style transfer are effective in hiding user identifiers, iris style transfer, with higher computation cost, outperforms others in both utility tasks, and is more resilient against spoof attacks. Our analyses indicate that there is no universal optimal approach to balance privacy, utility, and computation burden. Therefore, we recommend practitioners consider the strengths and weaknesses of each approach, and possible combinations of those to reach an optimal privacy-utility trade-off.

cs.CV↗

arXiv2025

Iris Style Transfer: Enhancing Iris Recognition with Style Features and Privacy Preservation through Neural Style Transfer

Iris texture is widely regarded as a gold standard biometric modality for authentication and identification. The demand for robust iris recognition methods, coupled with growing security and privacy concerns regarding iris attacks, has escalated recently. Inspired by neural style transfer, an advanced technique that leverages neural networks to separate content and style features, we hypothesize that iris texture's style features provide a reliable foundation for recognition and are more resilient to variations like rotation and perspective shifts than traditional approaches. Our experimental results support this hypothesis, showing a significantly higher classification accuracy compared to conventional features. Further, we propose using neural style transfer to obfuscate the identifiable iris style features, ensuring the protection of sensitive biometric information while maintaining the utility of eye images for tasks like eye segmentation and gaze estimation. This work opens new avenues for iris-oriented, secure, and privacy-aware biometric systems.

cs.CV↗

arXiv2025

Modeling Challenging Patient Interactions: LLMs for Medical Communication Training

Effective patient communication is pivotal in healthcare, yet traditional medical training often lacks exposure to diverse, challenging interpersonal dynamics. To bridge this gap, this study proposes the use of Large Language Models (LLMs) to simulate authentic patient communication styles, specifically the "accuser" and "rationalizer" personas derived from the Satir model, while also ensuring multilingual applicability to accommodate diverse cultural contexts and enhance accessibility for medical professionals. Leveraging advanced prompt engineering, including behavioral prompts, author's notes, and stubbornness mechanisms, we developed virtual patients (VPs) that embody nuanced emotional and conversational traits. Medical professionals evaluated these VPs, rating their authenticity (accuser: $3.8 \pm 1.0$; rationalizer: $3.7 \pm 0.8$ on a 5-point Likert scale (from one to five)) and correctly identifying their styles. Emotion analysis revealed distinct profiles: the accuser exhibited pain, anger, and distress, while the rationalizer displayed contemplation and calmness, aligning with predefined, detailed patient description including medical history. Sentiment scores (on a scale from zero to nine) further validated these differences in the communication styles, with the accuser adopting negative ($3.1 \pm 0.6$) and the rationalizer more neutral ($4.0 \pm 0.4$) tone. These results underscore LLMs' capability to replicate complex communication styles, offering transformative potential for medical education. This approach equips trainees to navigate challenging clinical scenarios by providing realistic, adaptable patient interactions, enhancing empathy and diagnostic acumen. Our findings advocate for AI-driven tools as scalable, cost-effective solutions to cultivate nuanced communication skills, setting a foundation for future innovations in healthcare training.

cs.HC↗

arXiv2025

CUIfy the XR: An Open-Source Package to Embed LLM-powered Conversational Agents in XR

Recent developments in computer graphics, machine learning, and sensor technologies enable numerous opportunities for extended reality (XR) setups for everyday life, from skills training to entertainment. With large corporations offering affordable consumer-grade head-mounted displays (HMDs), XR will likely become pervasive, and HMDs will develop as personal devices like smartphones and tablets. However, having intelligent spaces and naturalistic interactions in XR is as important as technological advances so that users grow their engagement in virtual and augmented spaces. To this end, large language model (LLM)--powered non-player characters (NPCs) with speech-to-text (STT) and text-to-speech (TTS) models bring significant advantages over conventional or pre-scripted NPCs for facilitating more natural conversational user interfaces (CUIs) in XR. This paper provides the community with an open-source, customizable, extendable, and privacy-aware Unity package, CUIfy, that facilitates speech-based NPC-user interaction with widely used LLMs, STT, and TTS models. Our package also supports multiple LLM-powered NPCs per environment and minimizes latency between different computational models through streaming to achieve usable interactions between users and NPCs. We publish our source code in the following repository: https://gitlab.lrz.de/hctl/cuify

cs.HC↗

arXiv2025

From Passive Watching to Active Learning: Empowering Proactive Participation in Digital Classrooms with AI Video Assistant

In online education, innovative tools are crucial for enhancing learning outcomes. SAM (Study with AI Mentor) is an advanced platform that integrates educational videos with a context-aware chat interface powered by large language models. SAM encourages students to ask questions and explore unclear concepts in real time, offering personalized, context-specific assistance, including explanations of formulas, slides, and images. We evaluated SAM in two studies: one with 25 university students and another with 80 crowdsourced participants, using pre- and post-knowledge tests to compare a group using SAM and a control group. The results demonstrated that SAM users achieved greater knowledge gains specifically for younger learners and individuals in flexible working environments, such as students, supported by a 97.6% accuracy rate in the chatbot's responses. Participants also provided positive feedback on SAM's usability and effectiveness. SAM's proactive approach to learning not only enhances learning outcomes but also empowers students to take full ownership of their educational experience, representing a promising future direction for online learning tools.

cs.AI↗

arXiv2025

Towards Adaptive Feedback with AI: Comparing the Feedback Quality of LLMs and Teachers on Experimentation Protocols

Effective feedback is essential for fostering students' success in scientific inquiry. With advancements in artificial intelligence, large language models (LLMs) offer new possibilities for delivering instant and adaptive feedback. However, this feedback often lacks the pedagogical validation provided by real-world practitioners. To address this limitation, our study evaluates and compares the feedback quality of LLM agents with that of human teachers and science education experts on student-written experimentation protocols. Four blinded raters, all professionals in scientific inquiry and science education, evaluated the feedback texts generated by 1) the LLM agent, 2) the teachers and 3) the science education experts using a five-point Likert scale based on six criteria of effective feedback: Feed Up, Feed Back, Feed Forward, Constructive Tone, Linguistic Clarity, and Technical Terminology. Our results indicate that LLM-generated feedback shows no significant difference to that of teachers and experts in overall quality. However, the LLM agent's performance lags in the Feed Back dimension, which involves identifying and explaining errors within the student's work context. Qualitative analysis highlighted the LLM agent's limitations in contextual understanding and in the clear communication of specific errors. Our findings suggest that combining LLM-generated feedback with human expertise can enhance educational practices by leveraging the efficiency of LLMs and the nuanced understanding of educators.

cs.AI↗

arXiv2025

Europe's AI Imperative -- A Pragmatic Blueprint for Global Tech Leadership

Europe is at a make-or-break moment in the global AI race, squeezed between the massive venture capital and tech giants in the US and China's scale-oriented, top-down drive. At this tipping point, where the convergence of AI with complementary and synergistic technologies, like quantum computing, biotech, VR/AR, 5G/6G, robotics, advanced materials, and high-performance computing, could upend geopolitical balances, Europe needs to rethink its AI-related strategy. On the heels of the AI Action Summit 2025 in Paris, we present a sharp, doable strategy that builds upon Europe's strengths and closes gaps.

cs.CY↗

arXiv2025

Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images

We explore the transformative potential of SAM 2, a vision foundation model, in advancing gaze estimation and eye tracking technologies. By significantly reducing annotation time, lowering technical barriers through its ease of deployment, and enhancing segmentation accuracy, SAM 2 addresses critical challenges faced by researchers and practitioners. Utilizing its zero-shot segmentation capabilities with minimal user input-a single click per video-we tested SAM 2 on over 14 million eye images from diverse datasets, including virtual reality setups and the world's largest unified dataset recorded using wearable eye trackers. Remarkably, in pupil segmentation tasks, SAM 2 matches the performance of domain-specific models trained solely on eye images, achieving competitive mean Intersection over Union (mIoU) scores of up to 93% without fine-tuning. Additionally, we provide our code and segmentation masks for these widely used datasets to promote further research.

cs.CV↗

arXiv2024

Benchmarking Large Language Models for Math Reasoning Tasks

The use of Large Language Models (LLMs) in mathematical reasoning has become a cornerstone of related research, demonstrating the intelligence of these models and enabling potential practical applications through their advanced performance, such as in educational settings. Despite the variety of datasets and in-context learning algorithms designed to improve the ability of LLMs to automate mathematical problem solving, the lack of comprehensive benchmarking across different datasets makes it complicated to select an appropriate model for specific tasks. In this project, we present a benchmark that fairly compares seven state-of-the-art in-context learning algorithms for mathematical problem solving across five widely used mathematical datasets on four powerful foundation models. Furthermore, we explore the trade-off between efficiency and performance, highlighting the practical applications of LLMs for mathematical reasoning. Our results indicate that larger foundation models like GPT-4o and LLaMA 3-70B can solve mathematical reasoning independently from the concrete prompting strategy, while for smaller models the in-context learning approach significantly influences the performance. Moreover, the optimal prompt depends on the chosen foundation model. We open-source our benchmark code to support the integration of additional models in future research.

cs.CL↗

arXiv2024

Imperceptible Gaze Guidance Through Ocularity in Virtual Reality

We introduce to VR a novel imperceptible gaze guidance technique from a recent discovery that human gaze can be attracted to a cue that contrasts from the background in its perceptually non-distinctive ocularity, defined as the relative difference between inputs to the two eyes. This cue pops out in the saliency map in the primary visual cortex without being overtly visible. We tested this method in an odd-one-out visual search task using eye tracking with 15 participants in VR. When the target was rendered as an ocularity singleton, participants' gaze was drawn to the target faster. Conversely, when a background object served as the ocularity singleton, it distracted gaze from the target. Since ocularity is nearly imperceptible, our method maintains user immersion while guiding attention without noticeable scene alterations and can render object's depth in 3D scenes, creating new possibilities for immersive user experience across diverse VR applications.

cs.HC↗

arXiv2024

Exploring Communication Dynamics: Eye-tracking Analysis in Pair Programming of Computer Science Education

Pair programming is widely recognized as an effective educational tool in computer science that promotes collaborative learning and mirrors real-world work dynamics. However, communication breakdowns within pairs significantly challenge this learning process. In this study, we use eye-tracking data recorded during pair programming sessions to study communication dynamics between various pair programming roles across different student, expert, and mixed group cohorts containing 19 participants. By combining eye-tracking data analysis with focus group interviews and questionnaires, we provide insights into communication's multifaceted nature in pair programming. Our findings highlight distinct eye-tracking patterns indicating changes in communication skills across group compositions, with participants prioritizing code exploration over communication, especially during challenging tasks. Further, students showed a preference for pairing with experts, emphasizing the importance of understanding group formation in pair programming scenarios. These insights emphasize the importance of understanding group dynamics and enhancing communication skills through pair programming for successful outcomes in computer science education.

cs.HC↗

arXiv2024

Can AI grade your essays? A comparative analysis of large language models and teacher ratings in multidimensional essay scoring

The manual assessment and grading of student writing is a time-consuming yet critical task for teachers. Recent developments in generative AI, such as large language models, offer potential solutions to facilitate essay-scoring tasks for teachers. In our study, we evaluate the performance and reliability of both open-source and closed-source LLMs in assessing German student essays, comparing their evaluations to those of 37 teachers across 10 pre-defined criteria (i.e., plot logic, expression). A corpus of 20 real-world essays from Year 7 and 8 students was analyzed using five LLMs: GPT-3.5, GPT-4, o1, LLaMA 3-70B, and Mixtral 8x7B, aiming to provide in-depth insights into LLMs' scoring capabilities. Closed-source GPT models outperform open-source models in both internal consistency and alignment with human ratings, particularly excelling in language-related criteria. The novel o1 model outperforms all other LLMs, achieving Spearman's $r = .74$ with human assessments in the overall score, and an internal consistency of $ICC=.80$. These findings indicate that LLM-based assessment can be a useful tool to reduce teacher workload by supporting the evaluation of essays, especially with regard to language-related criteria. However, due to their tendency for higher scores, the models require further refinement to better capture aspects of content quality.

cs.CL↗