Speaker
Siddharth Mishra-Sharma
(MIT)
Description
I will present a multi-modal model that associates astronomical observations imaged by the Hubble Space Telescope with natural language. I will show that the model embodies a meaningful joint representation between the highly-domain-specific images and text using a variety of downstream tasks. The model demonstrates the potential of using generalist rather than task-specific models in parts of the traditional research pipeline, in particular by leveraging text as an interface.
Primary author
Siddharth Mishra-Sharma
(MIT)
Co-authors
Jesse Thaler
(MIT)
Yiding Song
(MIT)
