• PhD candidate - AI psychology - XAI, biosignals, and personal experiences
• Surgeon - Neurophotonics lab - Zong Group - Kavli Institute for Systems Neuroscience (KISN).
• M.Sc. - Multimodal processing in higher-order brain regions.
• B.Sc. - Cognitive and Sleep Psychology.

____________________________________________

My Role

I am a PhD candidate in AI psychology, a field where we use intelligent systems to study and solve psychological problems that require intelligence - problems where, traditionally, the human brain alone provided the answers.

I develop interpretable AI tools for complex time-series data from human biosignals. My work combines deep learning with explainable AI (XAI) to make model outputs understandable and usable for researchers and domain experts who don't necessarily have an ML background.

A central question in my research is how explanations, limitations, and uncertainty should be designed and communicated when AI is used as decision support - particularly in contexts where human judgment and real-time signals intersect.

Large Language Models and Unethical AI

In parallel, I work with large language models (LLMs), including fine-tuning (LoRA), dataset design, and RAG. In my teaching, I also cover unethical and manipulative LLM behavior in a controlled manner, to expose risks, biases, and failure patterns, and to train master's students in responsible and safe AI development in Python.

(This text was, inevitably, generated by AI.)