6 citations · 9 across the 17 of their papers we have counts for
10 papers · 1 filter
Understanding the Inner Workings of Language Models Through Representation Dissimilarity
Davis Brown, Charles Godfrey, Nicholas Konz +2
As language models are applied to an increasing number of real-world applications, understanding their inner workings has become an important issue in model trust, interpretability…
Attributing Learned Concepts in Neural Networks to Training Data
Nicholas Konz, Charles Godfrey, Madelyn Shapiro +3
By now there is substantial evidence that deep learning models learn certain human-interpretable features as part of their internal representations of data. As having the right (or…
Impact of architecture on robustness and interpretability of multispectral deep neural networks
Charles Godfrey, Elise Bishoff, Myles McKay +1
Including information from additional spectral bands (e.g., near-infrared) can improve deep learning model performance for many vision-oriented tasks. There are many possible ways…
Neural Image Compression: Generalization, Robustness, and Spectral Biases
Kelsey Lieberman, James Diffenderfer, Charles Godfrey +1
Recent advances in neural image compression (NIC) have produced models that are starting to outperform classic codecs. While this has led to growing excitement about using NIC in r…
Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning
Elise Bishoff, Charles Godfrey, Myles McKay +1
In overhead image segmentation tasks, including additional spectral bands beyond the traditional RGB channels can improve model performance. However, it is still unclear how incorp…
How many dimensions are required to find an adversarial example?
Charles Godfrey, Henry Kvinge, Elise Bishoff +4
Past work exploring adversarial vulnerability have focused on situations where an adversary can perturb all dimensions of model input. On the other hand, a range of recent works co…
Fast computation of permutation equivariant layers with the partition algebra
Charles Godfrey, Michael G. Rawson, Davis Brown +1
Linear neural network layers that are either equivariant or invariant to permutations of their inputs form core building blocks of modern deep learning architectures. Examples incl…
Edit at your own risk: evaluating the robustness of edited models to distribution shifts
Davis Brown, Charles Godfrey, Cody Nizinski +2
The current trend toward ever-larger models makes standard retraining procedures an ever-more expensive burden. For this reason, there is growing interest in model editing, which e…
Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension
Henry Kvinge, Davis Brown, Charles Godfrey
Prompting has become an important mechanism by which users can more effectively interact with many flavors of foundation model. Indeed, the last several years have shown that well-…
Correspondences in log Hodge cohomology
Charles Godfrey
We construct correspondences in logarithmic Hodge theory over a perfect field of arbitrary characteristic. These are represented by classes in the cohomology of sheaves of differen…