Using cognitive science and social psychology to study human–AI interaction under uncertainty, with the goal of designing interpretable and trustworthy AI systems, especially in high-stakes and vulnerable contexts:
- 🧠 Cognitive Science — Investigating how people form beliefs, expectations, and mental models of AI behavior.
- 🧪 Social Psychology — Studying trust, attribution, responsibility, and perceived agency in human–AI interactions.
- 📐Computational Modeling — Formalizing psychological theory to support empirical investigation and model human reasoning.
- 🔍 Interpretability & Trust — Informing AI design to improve transparency, understanding, and user confidence.
- 🤖 Human-Centered AI (HCAI) — Ensuring AI systems align with human values in socially and ethically sensitive settings.
Building AI agents that model user beliefs and intentions for proactive assistance Stack:
|
Auditing framework for detecting algorithmic bias in career recommendation systems Stack:
|
|
Real-time cognitive load detection from user interaction patterns Stack:
|
Transformer-based framework for discovering novel antimicrobial peptides effective against WHO priority pathogens. Stack:
|
| 📄 Publication | 📚 Venue | 🔗 Links |
|---|---|---|
| UNET-Based Segmentation for Diabetic Macular Edema Detection in OCT Images | ICCIS 2025, Springer LNNS |   |
