Center for Decoding the Universe Quarterly Forum

We are soliciting abstracts for short talks at the Forum. If you want to be considered for a talk, please submit a tentative title and abstract by January 16th, 5:00 PM (Pacific Time).

The Center for Decoding the Universe brings together researchers across scientific disciplines to answer the biggest questions about our Universe by leveraging complex data with the most advanced computational methods. The Center’s second quarterly forum will focus on three data science and artificial intelligence topics that will help us answer these questions.

The first session will explore forward modeling techniques that (i) incorporate constraints imposed by the laws of nature and (ii) use AI to learn about these laws. We will explore connections between 3D scene-rendering systems that perceive and reason about the physical world and a 3D digital twin of our universe, constructed from billions of 2D projected images. 

Confirmed speakers: Jiajun Wu, Tom Abel

The second session will focus on discovery and inference from multi-modal data. It will connect the modeling of dynamic, living systems to the encoding of multi-wavelength observations of nearby galaxies collected through various telescopes.

Confirmed speakers: Ellen Kuhl, Dalya Baron

Finally, our Agentic AI for Science session will explore recent breakthroughs in large language models and multi-agent systems to accelerate scientific discovery, from hypothesis generation to experimental protein design. We will explore how these advances can drive innovation in astronomy, which has a strong culture of open data, open-access publications, and open-source tools. 

Confirmed speakers: James Zou, Jo Ciuca, Sandy Yuan

The Forum will begin with lunch at noon. The main program will run from 1:00 - 5:00 PM, and a reception will follow.

Detailed agenda coming soon! 

Our inaugural forum took place in the fall of 2024. Read a summary and watch the talks.