About
Welcome! We are a research group based at Dartmouth College's Department of Computer Science in beautiful Hanover, New Hampshire.
Our lab studies the first-mile and last-mile problems of AI systems (e.g. agents) in human environments.
The first mile is about grounding: how AI systems build persistent memory, world models, and personalized representations from ambiguous, preference-rich human contexts. We study how to measure and improve these internal structures so that agent behavior is coherent, adaptable, and aligned with evolving human goals.
The last mile is about integration: how AI systems can act robustly, remain steerable and reliable when embedded in real-world workflows, incentives, and open-ended tasks in interactive settings.
We treat this as both a scientific and a design problem space, and call this dual focus the science and art of human-AI systems.
Our work is domain-general, and currently we focus on testbeds where ambiguity and human preference are paramount, such as music creation, healthcare, and agent-based decision-making.
Keywords: Machine Learning, Human-Computer Interaction, Human Behavior, Creativity, Generative Models, Interactive Systems, Interpretability, Steerability, Human-AI Collaboration, Augmented Intelligence, Cognitive Tools, Human-Centered AI, Human-AI Co-Evolution, Human-in-the-Loop Systems
साहस • (sāhas) — stem noun: a Hindi word often translated as courage, intrepidity, principled boldness. The resolve to confront uncertainty with inner strength.
Research Pillars
We work across the stack of human-AI systems:
The first mile of AI capabilities
Hover to expand
What internal structure allows agents to model people and the world over time?
The last mile of AI behavior
Hover to expand
How can agents remain controllable and interpretable when embedded in real workflows?
Closing the loop of human-AI co-adaptation
Hover to expand
How do AIs and humans co-adapt over time?