Events

Speaker: Monica Agrawal

What if a machine could watch a video and write down the equations of motion? I’ll discuss our recent work toward this goal — systems that learn to discover the hidden state variables and governing dynamics directly from raw visual data. These discovered Neural State Variables and Neural State Vector Fields not only reproduce trajectories but also reveal the structure of these dynamical systems: equilibrium, stability, and chaos. The results suggest a path toward a self-driven AI scientist.

This talk will present recent advances in quantitative MRI and physics-based image synthesis as a foundation for pan-contrast AI.

This talk will focus on a few examples of blood vessels and how understanding their motions have led to improvements in medical device development and patient care.  In addition, I’ll share some of the top lessons I’ve learned as an entrepreneur.

Topic to be announced

As in-patient environments generate vast amounts of heterogeneous data, ranging from continuous physiological telemetry to sparsely sampled medical imaging, there is a profound opportunity to translate this information into actionable clinical foresight. This talk will focus on the development of novel foundation models and transformer architectures designed to handle the temporal complexities of longitudinal hospital data.