Research Group Enkelejda Kasneci
Enkelejda Kasneci
is a Liesel Beckmann Distinguished Professor of Human-Centered Technologies for Learning at TU Munich.
Her research focuses on human-centered technologies, emphasizing the crossroads between multimodal interaction and cutting-edge technological tools like VR, AR, and eye-tracking methodologies. Her group incorporates AI to foster and facilitate the emergence of innovative learning paradigms and interactive systems that can revolutionize how we learn and interact with media and assistive technologies in our everyday lives.
Team members @MCML
PostDocs
PhD Students
Recent News @MCML
Publications @MCML
2026
[22]
E. Kasneci • G. Kasneci
Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
[21]
I. Bueno • B. Bühler • P. Stark • T. Fütterer • U. Trautwein • D. Demszky • H. Hill • E. Kasneci
From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL
From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment.
Findings @ACL 2026 - Findings at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. To be published. Preprint available. URL
[20]
I. Bueno • L. Hirlimann • E. Kasneci
MemeScouts@LT-EDI 2026: Asking the Right Questions -- Prompted Weak Supervision for Meme Hate Speech Detection.
LT-EDI @ACL 2026 - 6th Workshop on Language Technology for Equality, Diversity and Inclusion at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. PDF GitHub
MemeScouts@LT-EDI 2026: Asking the Right Questions -- Prompted Weak Supervision for Meme Hate Speech Detection.
LT-EDI @ACL 2026 - 6th Workshop on Language Technology for Equality, Diversity and Inclusion at the 64th Annual Meeting of the Association for Computational Linguistics. San Diego, CA, USA, Jul 02-07, 2026. PDF GitHub
[19]
K. H. C. Lau • N. Terzimehić • E. Kasneci
PromptMirror: Visualizing LLM Use to Support STEM Student Reflection.
DIS 2026 - ACM Conference on Designing Interactive Systems. Singapore, Singapore, Jun 14-17, 2026. To be published. Preprint available. PDF
PromptMirror: Visualizing LLM Use to Support STEM Student Reflection.
DIS 2026 - ACM Conference on Designing Interactive Systems. Singapore, Singapore, Jun 14-17, 2026. To be published. Preprint available. PDF
[18]
V. Maquiling • Y. Abdrabou • E. Kasneci
As Far as Eye See: Vergence-Pupil Coupling in Near-Far Depth Switching.
ETRA 2026 - ACM Symposium on Eye Tracking Research and Applications. Marrakech, Morocco, Jun 01-04, 2026. To be published. Preprint available. arXiv
As Far as Eye See: Vergence-Pupil Coupling in Near-Far Depth Switching.
ETRA 2026 - ACM Symposium on Eye Tracking Research and Applications. Marrakech, Morocco, Jun 01-04, 2026. To be published. Preprint available. arXiv
[17]
F. Kaltenberger • W.-L. Chen • E. Thaqi • E. Kasneci
Sure About That Line? Approaching Confidence-Based, Real-Time Line Assignment in Reading Gaze Data.
Proceedings of the ACM on Computer Graphics and Interactive Techniques 9.2. May. 2026. DOI
Sure About That Line? Approaching Confidence-Based, Real-Time Line Assignment in Reading Gaze Data.
Proceedings of the ACM on Computer Graphics and Interactive Techniques 9.2. May. 2026. DOI
[16]
K. H. C. Lau • E. Bozkir • P. Stark • E. Kasneci
Skin-Deep Bias: How Avatar Appearances Shape Perceptions of AI Hiring.
CHI 2026 - ACM CHI Conference on Human Factors in Computing Systems. Barcelona, Spain, Apr 13-17, 2026. DOI
Skin-Deep Bias: How Avatar Appearances Shape Perceptions of AI Hiring.
CHI 2026 - ACM CHI Conference on Human Factors in Computing Systems. Barcelona, Spain, Apr 13-17, 2026. DOI
[15]
K. H. C. Lau • E. Kasneci
What Shapes Participant Data Quality? A Scoping Review and Case Study of Crowdsourced Webcam Eye Tracking in AI Interviews.
CHI 2026 - ACM CHI Conference on Human Factors in Computing Systems. Barcelona, Spain, Apr 13-17, 2026. DOI
What Shapes Participant Data Quality? A Scoping Review and Case Study of Crowdsourced Webcam Eye Tracking in AI Interviews.
CHI 2026 - ACM CHI Conference on Human Factors in Computing Systems. Barcelona, Spain, Apr 13-17, 2026. DOI
[14]
Z. T. Zhang • N. von Felten • L. Reicherts • L. Tankelevitch • Z. Guan • S. Rintel • Y. Fu • J. He • K. Holstein • A. Sarkar • G. Ramos • A. Schmitt • A. Singh • H. Li • S. Palani • P. Dalsgaard
Tools for Thought: Understanding, Protecting, and Augmenting Human Cognition with Generative AI—From Vision to Implementation.
CHI 2026 - ACM CHI Conference on Human Factors in Computing Systems. Barcelona, Spain, Apr 13-17, 2026. Extended Abstract. DOI
Tools for Thought: Understanding, Protecting, and Augmenting Human Cognition with Generative AI—From Vision to Implementation.
CHI 2026 - ACM CHI Conference on Human Factors in Computing Systems. Barcelona, Spain, Apr 13-17, 2026. Extended Abstract. DOI
[13]
A. Bodonhelyi • A. Curinier • B. Bühler • G. Anders • L. Rausch • M. Huff • U. Trautwein • R. Ewerth • P. Gerjets • E. Kasneci
Automatic Mind Wandering Detection in Educational Settings: A Systematic Review and Multimodal Benchmarking.
Preprint (Apr. 2026). arXiv
Automatic Mind Wandering Detection in Educational Settings: A Systematic Review and Multimodal Benchmarking.
Preprint (Apr. 2026). arXiv
[12]
D. Guo • Y. Abdrabou • E. Kasneci
Lazy or Efficient? Towards Accessible Eye-Tracking Event Detection Using LLMs.
Preprint (Apr. 2026). arXiv
Lazy or Efficient? Towards Accessible Eye-Tracking Event Detection Using LLMs.
Preprint (Apr. 2026). arXiv
[11]
V. Maquiling • Y. Abdrabou • E. Kasneci
Night Eyes: A Reproducible Framework for Constellation-Based Corneal Reflection Matching.
Preprint (Apr. 2026). arXiv
Night Eyes: A Reproducible Framework for Constellation-Based Corneal Reflection Matching.
Preprint (Apr. 2026). arXiv
[10]
S. Ozdel • V. Maquiling • K. Buldu • Y. Abdrabou • E. Kasneci
VIVA Stimuli: A Web-Based Platform for Eye Tracking Stimuli.
Preprint (Apr. 2026). arXiv GitHub
VIVA Stimuli: A Web-Based Platform for Eye Tracking Stimuli.
Preprint (Apr. 2026). arXiv GitHub
[9]
S. Ozdel • A. Nader • Y. Abdrabou • E. Kasneci
Secure Storage and Privacy-Preserving Scanpath Comparison via Garbled Circuits in Eye Tracking.
Preprint (Apr. 2026). arXiv GitHub
Secure Storage and Privacy-Preserving Scanpath Comparison via Garbled Circuits in Eye Tracking.
Preprint (Apr. 2026). arXiv GitHub
[8]
D. Paker • S. Ozdel • E. Kasneci
Understanding Password Preferences, Memorability, and Security through a Human-Centered Lens.
Preprint (Apr. 2026). arXiv
Understanding Password Preferences, Memorability, and Security through a Human-Centered Lens.
Preprint (Apr. 2026). arXiv
[7]
X. Zhang • Y. Ye • Y. Ma • Z. T. Zhang • A. Butz
Beyond Information Amount: Rethinking Transparency through Active Reasoning Demand.
HRI 2026 - 21st ACM/IEEE International Conference on Human-Robot Interaction. Edinburgh, Scotland, UK, Mar 16-19, 2026. DOI
Beyond Information Amount: Rethinking Transparency through Active Reasoning Demand.
HRI 2026 - 21st ACM/IEEE International Conference on Human-Robot Interaction. Edinburgh, Scotland, UK, Mar 16-19, 2026. DOI
[6]
I. Bueno • R. Hou • B. Bühler • T. Fütterer • J. Drimalla • J. K. Foster • P. Youngs • P. Gerjets • U. Trautwein • E. Kasneci
Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data.
WACV 2026 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Mar 06-10, 2026. To be published. Preprint available. arXiv
Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data.
WACV 2026 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Mar 06-10, 2026. To be published. Preprint available. arXiv
[5]
M. Wang • E. Bozkir • E. Kasneci
CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning.
WACV 2026 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Mar 06-10, 2026. To be published. Preprint available. arXiv GitHub
CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning.
WACV 2026 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Mar 06-10, 2026. To be published. Preprint available. arXiv GitHub
[4]
B. Bühler • I. Bueno • E. Kasneci
Democratizing Writing Support with AI: Insights from One Year of Real-World Interactions with an Open-Access Writing Feedback Tool.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. DOI GitHub
Democratizing Writing Support with AI: Insights from One Year of Real-World Interactions with an Open-Access Writing Feedback Tool.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. DOI GitHub
2025
[3]
K. Li • M. Niemeyer • Z. Chen • N. Navab • F. Tombari
MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction.
Preprint (Nov. 2025). arXiv
MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction.
Preprint (Nov. 2025). arXiv
[2]
G. Zhang • M. Ding • J. Wu • R. Liao • V. Tresp
ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay.
Preprint (Nov. 2025). arXiv
ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay.
Preprint (Nov. 2025). arXiv
[1]
G. Zhang • M. Ding • T. Liu • Y. Zhang • V. Tresp
Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs.
Preprint (Feb. 2025). arXiv
Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs.
Preprint (Feb. 2025). arXiv
©all images: LMU | TUM
Back to Top
2025-10-06 - Last modified: 2026-07-03