Experience the latest tech and design innovations, built by Dartmouth students

You are invited to the Dartmouth Innovation and Technology Festival, where science, technology, energy, business, and the liberal arts intersect in the heart of the West End

In this talk, I address two concerns about neural text generation systems.

In this talk, I will present several recent results on “generalization metrics” to measure ML models.

I propose algorithms to learn indistinguishable probabilities, and show that they provably enable accurate risk assessment and better decision outcomes.

Jieyu's research analyzes the potential stereotypes in various ML models and develops computational approaches to enhance fairness in a wide range of NLP applications.

I will share research that demonstrates how we can use computational approaches and interventions to reduce political polarization and improve the health of conversations online.

In this talk I will discuss recent progress towards using human input to enable safe and robust autonomous systems.

Translating AI to Impact: Uncertainty and Human-agent Interactions in Multi-agent Systems for Public Health and Conservation - see abstract below.

In my research, I utilize graphics and physics-based rendering to explore this complex design space and create imaging systems that optimally sense multiply-scattered light.