Hi!
I’m Kyle Whitecross, a first-year PhD Student at the Manning CICS in UMass Amherst. I work at the Center for Intelligent Information Retrieval, where I am advised by Prof. Negin Rahimi. Previously, I was a B.S. student at UCLA in the Samueli School of Engineering, where I studied Computer Science
Research
Currently, I’m interested in leveraging graph machine learning to build more flexible and robust Retrieval-augmented Generation (RAG) systems. In the past, I have also worked on designing more expressive Graph Transformers with Prof. Rex Ying, compiling neural networks into tractable boolean circuits with Prof. Adnan Darwiche, and studying robustness to noisily labelled data with Prof. Baharan Mirzasoleiman. I also interned at Kumo.ai where I developed and deployed a method to automatically identify target leakage in large industry datasets.
News
- 04/2024 I just accepted an offer to join the CIIR lab as a PhD Student at UMass Amherst!
- 04/2024 My second paper, Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise was just accepted to UAI 2024!
- 06/2023 I graduated summa cum laude with a B.S. in Computer Science from the Henry Samueli School of Engineering and Applied Sciences at UCLA!
- 06/2022 I just started an internship at Kumo.ai in Mountain View, CA.
- 05/2022: My first paper, Investigating Why Contrastive Learning Benefits Robustness Against Label Noise was accepted to ICML 2022!