About Me

Hello! My name is Cassandra (Casey) Goldberg. I am a second-year computer science PhD student at the University of Pennsylvania, where I focus on trustworthy AI, particularly interpretability and representation learning. I am fortunate to be advised by Eric Wong, where I work as part of his Brachio Lab.

I previously earned my BA in computer science and physics at Bowdoin College. There, I researched statistically-sound deep learning techniques for synthetic aperture radar (SAR) image segmentation under the mentorship of Jeová Farias.

Recent News!

• December 2025: We will present our paper “SuperActivators: Only the Tail of the Distribution Contains Reliable Concept Signals” at the MechInterp Workshop @ NeurIPS 2025.
• October 2025: Our paper “A Parameter Estimation-Inspired Convolutional Block for SAR Data” will appear at IEEE SIBGRAPI 2025.
• May 2024: I completed my senior Honors Project, ‘Statistically Principled Deep Learning for SAR Image Segmentation,’ which can be found in Bowdoin Digital Commons.
• February 2024: I was honored to be chosen as an AAAI-24 Undergraduate Consortium Scholar, where I had the opportunity to attend the conference and present a project proposal which is published in their Conference Proceedings.

Publications and Preprints

• SuperActivators: Only the Tail of the Distribution Contains Reliable Concept Signals
  Cassandra Goldberg, Chaehyeon Kim, Adam Stein, Eric Wong
  Pre-print, 2025 · MechInterp Workshop @ NeurIPS, 2025
• A Parameter Estimation-Inspired Convolutional Block for SAR Data
  Cassandra Goldberg, J. F. S. Rocha Neto
  IEEE SIBGRAPI, 2025