1 citations · 2 across the 5 of their papers we have counts for
5 papers
Neural Architecture Codesign for Fast Physics Applications
Jason Weitz, Dmitri Demler, Luke McDermott +2
We develop a pipeline to streamline neural architecture codesign for physics applications to reduce the need for ML expertise when designing models for novel tasks. Our method empl…
Neural Architecture Codesign for Fast Bragg Peak Analysis
Luke McDermott, Jason Weitz, Dmitri Demler +3
We develop an automated pipeline to streamline neural architecture codesign for fast, real-time Bragg peak analysis in high-energy diffraction microscopy. Traditional approaches, n…
UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification
Jennifer Crawford, Haoli Yin, Luke McDermott +1
Multimodal Re-Identification (ReID) is a popular retrieval task that aims to re-identify objects across diverse data streams, prompting many researchers to integrate multiple modal…
Linear Mode Connectivity in Sparse Neural Networks
Luke McDermott, Daniel Cummings
With the rise in interest of sparse neural networks, we study how neural network pruning with synthetic data leads to sparse networks with unique training properties. We find that…
GraFT: Gradual Fusion Transformer for Multimodal Re-Identification
Haoli Yin, Jiayao Li, Eva Schiller +2
Object Re-Identification (ReID) is pivotal in computer vision, witnessing an escalating demand for adept multimodal representation learning. Current models, although promising, rev…