I'm an academic working in natural language processing, computer vision, and robotics. My research centers on building trustworthy AI systems by revealing how they work internally.
Right now, I'm exploring interpretability for embodied intelligence. I ask questions like: How do physical agents perceive and interact with their environment? What mechanisms drive their decision making?
I have extensive experience with frameworks such as:
Some of my key projects include:
| Eidos | BiasX | Teleman |
|---|---|---|
|
|
|
| A conversational agent that leverages transformer-based models to analyze inconsistencies within the belief system of philosophy students. | A statistical framework that applies explainable AI techniques to detect and quantify gender biases in face recognition systems. | A mobile robotics platform that uses Arduino microcontroller and LoRaWAN protocol to deliver food supplies during disaster scenarios. |