Research

Research Interests:

• Explainable AI
  • Self-Explainable Architectures for CV and NLP tasks
  • Explaining Vision Language Models and their decisions
• Understanding the limitations of Vision Language Models
  • Visual perception
  • Difference/Similarity comprehension

During my Master’s, I worked on Reinforcement Learning (RL) and Robotics, where my goal was to help robotic platforms acquire complex skills via RL.

Research To Date:

As part of my Ph.D. research, I am working on self-explainable and editable models for downstream CV/NLP tasks. More specifically, my research centers on the interpretability of minimal transformer layers (attention bottlenecks). I aim to use these bottlenecks so users can edit, debug and intervene in AI’s decision making.