4 papers
LoRA Enhanced Contrastive Learning with SAS Vision Transformers
Dan Zimmerman, Frank E. Bobe, Amelia L. McCormack +2
Automatic target recognition (ATR) with synthetic aperture sonar (SAS) supports advanced naval capabilities, but deep learning is constrained by scarce target imagery, background c…
Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models
Frank E. Bobe, Gregory D. Vetaw, Darshan W. Bryner +2
Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a framework that uses Logit Len…
A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar
C. J. Moore, Gregory D. Vetaw, Jordan Malof
In this work we study Automatic Target Recognition (ATR) for Synthetic Aperture Sonar (SAS) data with a focus on deep neural networks (DNNs). The main challenge in training DNNs fo…
Diagnosing Generalization Failures in Fine-Tuned LLMs: A Cross-Architectural Study on Phishing Detection
Frank Bobe, Gregory D. Vetaw, Chase Pavlick +3
The practice of fine-tuning Large Language Models (LLMs) has achieved state-of-the-art performance on specialized tasks, yet diagnosing why these models become brittle and fail to…