Luke McDermott

Hi. I'm a first year ML PhD student in UCSD's ECE Department, co-advised by Rahul Parhi & Robert Heath. Previously, I was a research scientist at Modern Intelligence and completed my undergrad at UCSD in Math-CS.

I am interested in developing efficient deep learning models, incorporating sparsity and plasticity to create adaptive, lifelong AI. Currently, I am interested in developing stronger forms of associative memory.

Selected Work

Linear Mode Connectivity in Sparse Neural Networks
by Luke McDermott & Daniel Cummings.
Accepted in NeurIPS 2023's UniReps Workshop.

Neural Architecture Codesign for Fast Bragg Peak Analysis
by L. McDermott, J. Weitz, D. Demler, D. Cummings, N. Tran, J. Duarte.
Accepted for spotlight presentation in AAAI 2024's Workshop on AI for Accelerating Science & Engineering.

UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification
by J. Crawford, H. Yin, L. McDermott, D. Cummings.
Accepted at NeurIPS 2023's UniReps Workshop.

Contact

• lmcdermo@ucsd.edu
• Google Scholar
• X/Twitter
• Linkedin

Feel free to reach out for questions or collaborations.