Projects

Beyond the ChatBot

Advancing Education through Interactive AI-Enhanced Learning Experiences

This project represents my first independently funded research initiative, in which I explore the ethical and pedagogically sound integration of LLMs into introductory programming education for non-computer science undergraduates. Grounded in principles of human-computer interaction and user experience design, my work focuses on developing novel interaction paradigms that support conceptual understanding while mitigating misuse with the aim of advancing responsible and impactful AI use in education.
Funded by: Swiss National Science Foundation (Grant No. 228765)
Project page: EduLLM (Beyond the ChatBot)

Interface-AR

Enhancing Pediatric Emergency Care with Augmented Reality

I lead user-experience research and data analysis for the Interface-AR system, focusing on improving team communication and procedural accuracy during pediatric cardiac resuscitation scenarios using augmented reality technologies.
Funded by: Swiss National Science Foundation (Grant No. 10002119)

Patients In My Pocket

Toward Laboratory Notification in Pediatric Emergency Departments

I co-led the design, analysis, and reporting of a comprehensive study examining how laboratory results are accessed in pediatric emergency departments.
Funded by: Internal institutional resources at University Hospitals of Geneva and University of Geneva.

Accompany

Supporting Parents of Adolescents with Anorexia through Interactive Serious Gaming

As the project’s PostDoc and manager, I oversee the user-experience design and integrate narrative-driven dialogues powered by LLMs to deliver a realistic, supportive training environment for caregivers.
Official website: accompany.unige.ch
Funded by: Swiss National Science Foundation (Grant No. 212661)

MOOC: Introduction to Programming

Massive Open Online Courses in French on Programming with Scala

I developed and coordinated the “Introduction à la Programmation” MOOC, designing comprehensive learning materials, videos scenarios, and assessments delivered through Coursera, enabling over 1,700 learners to effectively acquire foundational programming skills. Used as a SPOC at the University of Geneva.
Available on Moodle
Funded internally by the University of Geneva

AGE-INT

Innovative Digital Solutions to Enhance Healthy Aging

My contribution involved collaborating closely with Geneva-based gerontology and technology experts to explore how various stakeholders utilize technology in elder care, identifying key insights and opportunities for improvement. Co-Organized the first summer school on Design of Assistive Technologies for the Ageing Population: A transdisciplinary Training.
Official website: age-int.ch
Funded by: Swiss State Secretariat for Education, Research and Innovation

Guardian-AAL

Socially Assistive Robots Enhancing Independent Living for Older Adults

I developed emotion-recognition capabilities for Guardian robots, enabling them to understand and react to emotional states in elderly users, significantly improving personalized care and interaction quality.
Official website: guardian-aal.eu
Funded by: European Active Assisted Living (AAL) Programme

Smarpthone QoE: MiQ Model

Predicting and Improving Mobile Internet Quality of Experience

I created an advanced context-aware predictive model that anticipates and addresses potential declines in mobile app performance, significantly enhancing user satisfaction through proactive QoE management.
Project presented at international conferences and detailed extensively in my doctoral dissertation.
Funded by: Swiss National Science Foundation (Grant No. 157003)

EduLLM (Spark): Beyond the ChatBot

I am leading EduLLM (Beyond the ChatBot) under the SNSF Spark grant to rethink how large language models can support non-computer science students as they learn introductory programming. The goal is to move past generic chatbots and design evidence-based interactions that respect pedagogy, ethics, and students’ confidence. Why this project Many learners rely on ad-hoc chatbot answers that can be misleading or counter-productive. Educators need guardrails that align with their course design, assessment policies, and academic integrity expectations. HCI-driven experimentation can show where generative feedback helps or harms early-stage learners. What we’re building LLM-mediated learning flows that scaffold problem-solving steps instead of providing full solutions. Ethical and transparency layers so students understand model limits, provenance of hints, and acceptable use. Instructor controls to tune guidance levels, restrict disallowed prompts, and surface analytics about help-seeking behaviors. Benchmarks and rubrics tailored to novice errors in Scala and Python exercises to evaluate LLM responses. Research approach Mixed-method classroom studies combining telemetry, think-aloud protocols, and graded outcomes to measure effectiveness and trust. Iterative prototyping with rapid A/B comparisons of prompt strategies, moderation filters, and UI cues. Funding and collaboration Funded by the Swiss National Science Foundation (Grant No. 228765). If you’re teaching introductory programming and want to collaborate on trials or share datasets of student questions, feel free to reach out.