about me
I am a postdoc at Stanford University, working at the intersection of AI, health, and food. I am passionate about the application of AI for social good and specifically interested in designing trustworthy AI systems for critical applications like healthcare and robotics. I finished my Ph.D. in Algorithms for human-robot interaction in August 2019.
It is important that we enable powerful AI systems to imbibe human values if we want to avoid any unintended consequences of the AI revolution. However, it is not easy to specify human values in a way that AI can make use of. I have been working on enabling AI systems to learn human values autonomously. In my doctoral research, I designed novel interactions that would allow AI systems or robots to seek alternative forms of guidance from humans and develop active learning algorithms that will enable them to learn human values faster. As an Insight AI Fellow in 2019, I explored generative models for synthesizing dangerous driving trajectories.
More recently, the pandemic and the associated propagation of medical misinformation got me interested in AI for healthcare. One of the stepping stones towards making authentic medical information more accessible is to simplify the knowledge for common people. My latest research on medical text simplification builds on the recent developments in controllable text generation to bridge the gap between online medical content generation and its accessibility.
My other projects include understanding human motivation behind food choices by mining food-related human values from textual content online. I am also working on an RL-based recommender system that can imbibe and manipulate these values to nudge people towards healthier eating.
Research Interests
AI for healthcare and robotics, Human-in-loop machine learning, Value Alignment, Trustworthy AI
ML METHODS
Natural Language Generation, Natural Language Understanding, Preference Learning, Recommender systems