7 citations · 15 across the 18 of their papers we have counts for
18 papers
MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
Jesse He, Helen Jenne, Max Vargas +4
The recent field of neural algorithmic reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical algorithms like Bellman-Ford, a phenomenon known as…
What do Geometric Hallucination Detection Metrics Actually Measure?
Eric Yeats, John Buckheit, Sarah Scullen +9
Hallucination remains a barrier to deploying generative models in high-consequence applications. This is especially true in cases where external ground truth is not readily availab…
Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction
Davis Brown, Jesse He, Helen Jenne +2
Evolutionary program synthesis systems such as AlphaEvolve, OpenEvolve, and ShinkaEvolve offer a new approach to AI-assisted mathematical discovery. These systems utilize teams of…
Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics
Herman Chau, Helen Jenne, Davis Brown +4
With recent dramatic increases in AI system capabilities, there has been growing interest in utilizing machine learning for reasoning-heavy, quantitative tasks, particularly mathem…
Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes
Jesse He, Helen Jenne, Herman Chau +4
Machine learning is becoming an increasingly valuable tool in mathematics, enabling one to identify subtle patterns across collections of examples so vast that they would be imposs…
Haldane Bundles: A Dataset for Learning to Predict the Chern Number of Line Bundles on the Torus
Cody Tipton, Elizabeth Coda, Davis Brown +5
Characteristic classes, which are abstract topological invariants associated with vector bundles, have become an important notion in modern physics with surprising real-world conse…
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…
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-…
Experimental Observations of the Topology of Convolutional Neural Network Activations
Emilie Purvine, Davis Brown, Brett Jefferson +6
Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of compl…
Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds
Henry Kvinge, Grayson Jorgenson, Davis Brown +2
While the last five years have seen considerable progress in understanding the internal representations of deep learning models, many questions remain. This is especially true when…
Testing predictions of representation cost theory with CNNs
Charles Godfrey, Elise Bishoff, Myles Mckay +4
It is widely acknowledged that trained convolutional neural networks (CNNs) have different levels of sensitivity to signals of different frequency. In particular, a number of empir…
The SVD of Convolutional Weights: A CNN Interpretability Framework
Brenda Praggastis, Davis Brown, Carlos Ortiz Marrero +3
Deep neural networks used for image classification often use convolutional filters to extract distinguishing features before passing them to a linear classifier. Most interpretabil…
On the Symmetries of Deep Learning Models and their Internal Representations
Charles Godfrey, Davis Brown, Tegan Emerson +1
Symmetry is a fundamental tool in the exploration of a broad range of complex systems. In machine learning symmetry has been explored in both models and data. In this paper we seek…
Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools
Davis Brown, Henry Kvinge
Methods for model explainability have become increasingly critical for testing the fairness and soundness of deep learning. Concept-based interpretability techniques, which use a s…