Hey, I'm Evan! πŸ‘‹πŸΌ

Evan

I am a computer science Ph.D. student at MIT. My research focuses on understanding what deep neural networks learn from large quantities of data: what concepts are encoded in their features, and how can we communicate the network's learned algorithm to humans? I am extremely fortunate to be advised by Jacob Andreas and to work closely with Antonio Torralba.

Before graduate school, I earned my B.S. in computer science and mathematics from the University of Wisconsin-Madison. There, I developed a natural language interface for the educational programming environment Blockly and studied how to synthesize example programs for students using a noisy, hand-drawn sketch as a specification.

I also worked for Google as a software engineer and contributed to Chromium.


Research

neuro descriptions
Evan Hernandez, Sarah Schwettmann, David Bau, Teona Bagashvili, Antonio Torralba, Jacob Andreas

We present a procedure to automatically generate natural language descriptions of neurons in computer vision models. These generated descriptions support important interpretability applications: we use them to analyze neuron importance, identify adversarial vulnerabilities, audit for unexpected features, and edit out spurious correlations.

visual concept vocabulary
+snow, +clouds
Sarah Schwettmann, Evan Hernandez, David Bau, Samuel Klein, Jacob Andreas, Antonio Torralba

GANs sometimes encode visual concepts in their latent space as linear directions. We construct a visual concept vocabulary for pretrained GANs, consisting of latent directions and free-form language descriptions of the changes they induce. We then distil the vocabulary into simpler, one-word visual concepts (e.g., snow or clouds).

low-dimensional subspace
Evan Hernandez, Jacob Andreas

How do word representations geometrically encode linguistic abstractions like part of speech? We find that many linguistic features are encoded in low-dimensional subspaces of contextual word representation spaces, and these subspaces can causally influence model predictions.


Teaching

Mentor[su'21]

I had the pleasure of mentoring an MSRP summer intern on a research project. She developed a language-based image editing tool for images generated by GANs.

6.864: Advanced Natural Language Processing
Teaching Assistant[sp'21]

MIT’s primary NLP course, typically taken after a first course in ML. I wrote homework assignments, planned recitations, and led weekly office hours.

Tutor, Programmer[fa'15 - sp'18]

For three years, I tutored underrepresented students in UW-Madison engineering programs on introductory computer science and math classes. I also developed tutoring software to support the tutoring by request and drop-in tutoring services.