2026 workshop program
Imaging at the Edge of Science: Integrating Scientific Knowledge and AI to Recover Hidden Structure
The work
Abstract
Images play a central role in scientific discovery.
Whether it’s astronomical, biological, or materials systems, bringing complex phenomena into view enables scientists to probe, model, and fundamentally understand them. However, many of the most important scientific questions lie at the edge of what can be directly observed.
We can accomplish extreme imaging through computational methods, bringing the invisible into view by supplementing limited observable data with human-imposed assumptions, or priors. When imaging for science, the challenge is imposing just enough known assumptions to infer the unknown.
I create principled methods for bringing advanced priors, such as scientific knowledge and AI, into computational imaging. Using astrophysics as a running example, this talk presents my vision for a framework in which scientists systematically explore different priors, understand their effects on imaging, and extract scientific insights.
The talk is organized in three parts.
Understanding the importance of priors in extreme scientific imaging. I present my work on leveraging generative AI to flexibly tune a knob between different priors and understand their effects on imaging. Applied to black-hole imaging, my approach lets us infer physical features of a real black hole by identifying image features that are robust to prior assumptions.
Carefully balancing scientific assumptions to solve an extreme imaging problem in astrophysics. I present Physics-informed Dynamic Emission Fields (PI-DEF), a method for imaging the dynamic 3D gas near a black hole. PI-DEF strikes a balance between known/unknown physics, imposing known physics as hard constraints on the solution while leaving room for learning unknown physics, such as the velocity field near the black hole.
Opening an efficient route for bringing in known physics across imaging problems. I present Neural Approximate Mirror Maps (NAMMs), which learn to automatically impose any desired physics constraint onto any image. With NAMMs, we can easily incorporate known constraints (e.g., conservation laws) into generated and reconstructed images.
The ideas of this talk naturally extend to many scientific domains, including biology, chemistry, and materials science.
The speaker
Biography
Berthy Feng is a postdoctoral researcher at MIT CSAIL and a fellow at the NSF Institute for AI and Fundamental Interactions (IAIFI), working with Prof. Bill Freeman. She received her PhD in Computational and Mathematical Sciences at Caltech, working with Prof. Katie Bouman. During her PhD, she was supported by the NSF GRFP and Kortschak Scholarship. Before that, she received her Bachelor’s degree in Computer Science at Princeton University. She builds computational imaging algorithms that integrate physics knowledge and AI to push the limits of what we can see.