Scott K. Geng
Hello, I'm Scott! I am a fourth-year undergrad studying math and computer science at Columbia University, where I am very fortunate to be advised by Prof. Junfeng Yang and Prof. Carl Vondrick.
I'm interested in teaching machines to reason robustly about open-world (and often multi-modal) data with as few labels as possible. Concretely, my current work focuses on using computer vision techniques to learn how humans interact from in-the-wild videos. My research is supported by the Rabi Fellowship.
Google Scholar  /
I've been lucky to explore research in several different fields during my time at Columbia. Currently, I work on engineering social intelligence and few-shot adversarial robustness at the Columbia Computer Vision Lab. Previously, I worked on program representation learning at the Software Systems Lab. And even further before that, I did research quantifying movement disorders with the Kuo Lab on Columbia's medical campus.
Understanding Zero-shot Adversarial
Robustness for Large-Scale Models
We identify the novel problem of zero-shot adversarial robustness and propose a new text-grounded adversarial training objective that can help make CLIP robust while preserving its ability to generalize.
NeuDep: Neural Binary Memory Dependence Analysis
Unlike in natural language, the semantic meaning of code is directly measureable as the CPU's memory values during runtime. Inferring these execution traces is a natural self-supervised task, which we can leverage to learn a nice representation of binary code.
Cerebellar Oscillations in Familial and Sporadic Essential Tremor
The Cerebellum, 2021
Low-frequency brain waves are correlated with symptom severity in sporadic essential tremor but not familial (i.e. genetic based). Suggests a difference in mechanism.
Jon Barron has a very clean website.
Last updated: October 1st, 2022.