Computational Neuroscientist · Human-Centered AI Researcher
Building neuroscience into human-centered AI systems for creativity and innovation.
About
I'm a Senior Research Scientist in Human-Centered AI at the Toyota Research Institute. My research sits at the intersection of behavioral science, neuroscience, and AI, combining theory- and data-driven approaches to investigate how context modulates learning and decision-making. I translate this work to building new technologies that help individuals and organizations meet their goals.
I'm particularly interested in motivation, flexible self regulation, and precision interventions for behavior change. I use diverse methods including neuroimaging, physiological monitoring, and experience sampling to sample and understand individual experience in context. I develop both novel elicitation methods and computational models, prioritizing diverse sensors and signals that can robustly capture human experience as it evolves over time. By leveraging varied signals and their dynamics across temporal and spatial contexts, my work improves understanding of complex psychological phenomena and identifies new, more precise targets for intervention.
My current work focuses on two questions:
Approach
I use a variety of signals to estimate each individual's internal experience as it evolves over time. By better understanding each individual in context, we can develop more precise, effective interventions to support their goals, values, and wellbeing.
How motivation, reward, and self-control shape learning and choice, with an emphasis on flexible, goal-directed decision making in real-world settings.
MotivationSelf regulationDecision scienceNeuroimagingDesigning, testing, and personalizing behavior-change interventions ranging from improving understanding of health risks to just-in-time support for psychological flexibility and creativity.
Behavior changeIntervention scienceCausalityDeveloping a mechanistic understanding of the process of creative work to promote not only innovation but also sustained creative wellbeing.
Creative cognitionDesign decision makingCreativity support toolsUsing psychological and neuroscientific theory to direct the underlying machinery of generative AI systems and better align their outputs with human thoughts and actions.
Human-AI alignmentActive inferenceBayesian surpriseNovel elicitation methods and models for understanding individual preferences from psychology, physiology, and behavior that account for context and time.
Decision scienceComplexityMachine learningImproved inference of humans' internal states and simulation of agent preferences to support human-AI teaming during complex tasks like driving.
Preference learningAgentic simulationHuman-AI teamingLeveraging psychographic and behavioral data, along with neural signals, to improve demand forecasting and product adoption, especially for innovative, new products.
EconometricsDemand forecastingNeuroforecastingModeling complex interactions between cognition and affect to understand and predict individual behavior in social contexts.
Social cognitionAffective processingIndividual differencesRecent Publications
Contact