Picture for Charles Godfrey

Charles Godfrey

Understanding the Inner Workings of Language Models Through Representation Dissimilarity

Add code
Oct 23, 2023
Viaarxiv icon

Attributing Learned Concepts in Neural Networks to Training Data

Add code
Oct 06, 2023
Viaarxiv icon

Impact of architecture on robustness and interpretability of multispectral deep neural networks

Add code
Sep 27, 2023
Viaarxiv icon

Neural Image Compression: Generalization, Robustness, and Spectral Biases

Add code
Jul 17, 2023
Figure 1 for Neural Image Compression: Generalization, Robustness, and Spectral Biases
Figure 2 for Neural Image Compression: Generalization, Robustness, and Spectral Biases
Figure 3 for Neural Image Compression: Generalization, Robustness, and Spectral Biases
Figure 4 for Neural Image Compression: Generalization, Robustness, and Spectral Biases
Viaarxiv icon

Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning

Add code
May 18, 2023
Viaarxiv icon

How many dimensions are required to find an adversarial example?

Add code
Mar 24, 2023
Figure 1 for How many dimensions are required to find an adversarial example?
Figure 2 for How many dimensions are required to find an adversarial example?
Figure 3 for How many dimensions are required to find an adversarial example?
Figure 4 for How many dimensions are required to find an adversarial example?
Viaarxiv icon

Fast computation of permutation equivariant layers with the partition algebra

Mar 10, 2023
Viaarxiv icon

Robustness of edited neural networks

Add code
Feb 28, 2023
Figure 1 for Robustness of edited neural networks
Figure 2 for Robustness of edited neural networks
Figure 3 for Robustness of edited neural networks
Figure 4 for Robustness of edited neural networks
Viaarxiv icon

Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension

Feb 16, 2023
Figure 1 for Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension
Figure 2 for Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension
Figure 3 for Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension
Figure 4 for Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension
Viaarxiv icon

Neural frames: A Tool for Studying the Tangent Bundles Underlying Image Datasets and How Deep Learning Models Process Them

Add code
Nov 19, 2022
Figure 1 for Neural frames: A Tool for Studying the Tangent Bundles Underlying Image Datasets and How Deep Learning Models Process Them
Figure 2 for Neural frames: A Tool for Studying the Tangent Bundles Underlying Image Datasets and How Deep Learning Models Process Them
Figure 3 for Neural frames: A Tool for Studying the Tangent Bundles Underlying Image Datasets and How Deep Learning Models Process Them
Figure 4 for Neural frames: A Tool for Studying the Tangent Bundles Underlying Image Datasets and How Deep Learning Models Process Them
Viaarxiv icon