HK
Henry Kvinge
cs.LGcs.CVcs.AImath.COmath.RTstat.MLcs.CLeess.IVeess.SPmath.AT
On Valency
published · living versionsW_42w3r2xd·v1 · currentpublished
Beyond Selected Breakthroughs: Evaluating Language Models on Randomly Sampled Mathematical Conjectures
with Helen Jenne, Davis Brown, Jesse He
1 version
Preprints & journals
63 papers in the corpus · 2015–2026Studying the Effects of Task Diversity Using Small Mathematical Worlds2610.13750v1 · Emily Xia Meng, Xuanyu Yang, Junaid Hasan et al.2026 · 0 citationsarXiv
PermuFormer: Multi-Task Pretraining for Permutation Representation in Algebraic Combinatorics2609.25438v1 · Henry Kvinge2026 · 0 citationsarXiv
The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs2608.27750v1 · Eric Yeats, Brendan Kennedy, Loc Truong et al.2026 · 0 citationsarXiv
TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning2607.28755v1 · Brendan Kennedy, Tegan Emerson, Gregory Roek et al.2026 · 0 citationsarXiv
Does My Embedding Reflect That ? Evaluating Mathematical Equivalence in Embedding Models2606.23959v2 · Jiaying Ye, Samarth Rao, Leo Carlin et al.2026 · 0 citationsarXiv
MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning2602.21442v1 · Jesse He, Helen Jenne, Max Vargas et al.2026 · 0 citationsarXiv
What do Geometric Hallucination Detection Metrics Actually Measure?2602.09158v1 · Eric Yeats, John Buckheit, Sarah Scullen et al.2026 · 0 citationsarXiv
Can Neural Networks Learn Small Algebraic Worlds? An Investigation Into the Group-theoretic Structures Learned By Narrow Models Trained To Predict Group Operations2601.21150v1 · Henry Kvinge, Andrew Aguilar, Nayda Farnsworth et al.2026 · 0 citationsarXiv
Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction2511.20987v1 · Davis Brown, Jesse He, Helen Jenne et al.2025 · 0 citationsarXiv
Saddle-Free Guidance: Improved On-Manifold Sampling without Labels or Additional Training2511.21863v1 · Eric Yeats, Darryl Hannan, Wilson Fearn et al.2025 · 0 citationsarXiv
Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge2507.07137v1 · Eric Yeats, Darryl Hannan, Henry Kvinge et al.2025 · 0 citationsarXiv
FMG-Det: Foundation Model Guided Robust Object Detection2505.23726v1 · Darryl Hannan, Timothy Doster, Henry Kvinge et al.2025 · 0 citationsarXiv
Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization2504.10727v1 · Darryl Hannan, John Cooper, Dylan White et al.2025 · 1 citationarXiv
Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics2503.06366v1 · Herman Chau, Helen Jenne, Davis Brown et al.2025 · 0 citationsarXiv
Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes2411.07467v3 · Jesse He, Helen Jenne, Herman Chau et al.2024 · 1 citationarXiv
ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain2409.05211v1 · Guillermo Bern'ardez, Lev Telyatnikov, Marco Montagna et al.2024 · 2 citationsarXiv
Model editing for distribution shifts in uranium oxide morphological analysis2407.15756v1 · Davis Brown, Cody Nizinski, Madelyn Shapiro et al.2024 · 0 citationsarXiv
Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities2406.05496v1 · Sai Munikoti, Ian Stewart, Sameera Horawalavithana et al.2024 · 10 citationsarXiv
Haldane Bundles: A Dataset for Learning to Predict the Chern Number of Line Bundles on the Torus2312.04600v1 · Cody Tipton, Elizabeth Coda, Davis Brown et al.2023 · 0 citationsarXiv
Understanding the Inner Workings of Language Models Through Representation Dissimilarity2310.14993v1 · Davis Brown, Charles Godfrey, Nicholas Konz et al.2023 · 2 citationsarXiv
Attributing Learned Concepts in Neural Networks to Training Data2310.03149v4 · Nicholas Konz, Charles Godfrey, Madelyn Shapiro et al.2023 · 0 citationsarXiv
ICML 2023 Topological Deep Learning Challenge : Design and Results2309.15188v4 · Mathilde Papillon, Mustafa Hajij, Helen Jenne et al.2023 · 0 citationsarXiv
SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions2307.01139v2 · Sameera Horawalavithana, Sai Munikoti, Ian Stewart et al.2023 · 19 citationsProc. 1st Workshop on Natural Language Processing for Science (NLP4Science 2024) (2024) 58-72
ColMix -- A Simple Data Augmentation Framework to Improve Object Detector Performance and Robustness in Aerial Images2305.13509v1 · Cuong Ly, Grayson Jorgenson, Dan Rosa de Jesus et al.2023 · 1 citationarXiv
How many dimensions are required to find an adversarial example?2303.14173v2 · Charles Godfrey, Henry Kvinge, Elise Bishoff et al.2023 · 4 citationsarXiv
Fast computation of permutation equivariant layers with the partition algebra2303.06208v1 · Charles Godfrey, Michael G. Rawson, Davis Brown et al.2023 · 0 citationsarXiv
Edit at your own risk: evaluating the robustness of edited models to distribution shifts2303.00046v2 · Davis Brown, Charles Godfrey, Cody Nizinski et al.2023 · 1 citationarXiv
Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension2302.09301v1 · Henry Kvinge, Davis Brown, Charles Godfrey2023 · 0 citationsarXiv
Parameters, Properties, and Process: Conditional Neural Generation of Realistic SEM Imagery Towards ML-assisted Advanced Manufacturing2302.08495v1 · Scott Howland, Lara Kassab, Keerti Kappagantula et al.2023 · 0 citationsarXiv
Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds2211.10558v2 · Henry Kvinge, Grayson Jorgenson, Davis Brown et al.2022 · 0 citationsarXiv
Do Neural Networks Trained with Topological Features Learn Different Internal Representations?2211.07697v1 · Sarah McGuire, Shane Jackson, Tegan Emerson et al.2022 · 3 citationsarXiv
In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?2210.03773v1 · Henry Kvinge, Tegan H. Emerson, Grayson Jorgenson et al.2022 · 5 citationsarXiv
Testing predictions of representation cost theory with CNNs2210.01257v3 · Charles Godfrey, Elise Bishoff, Myles Mckay et al.2022 · 0 citationsarXiv
On the Symmetries of Deep Learning Models and their Internal Representations2205.14258v5 · Charles Godfrey, Davis Brown, Tegan Emerson et al.2022 · 7 citationsarXiv
TopTemp: Parsing Precipitate Structure from Temper Topology2204.00629v2 · Lara Kassab, Scott Howland, Henry Kvinge et al.2022 · 0 citationsarXiv
Fiber Bundle Morphisms as a Framework for Modeling Many-to-Many Maps2203.08189v2 · Elizabeth Coda, Nico Courts, Colby Wight et al.2022 · 0 citationsarXiv
DNA: Dynamic Network Augmentation2112.09277v1 · Scott Mahan, Tim Doster, Henry Kvinge2021 · 0 citationsarXiv
Differential Property Prediction: A Machine Learning Approach to Experimental Design in Advanced Manufacturing2112.01687v1 · Loc Truong, WoongJo Choi, Colby Wight et al.2021 · 1 citationarXiv
Adaptive Transfer Learning: a simple but effective transfer learning2111.10937v1 · Jung H Lee, Henry J Kvinge, Scott Howland et al.2021 · 0 citationsarXiv
Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools2110.07120v2 · Davis Brown, Henry Kvinge2021 · 8 citationsarXiv
Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps2110.06983v3 · Nico Courts, Henry Kvinge2021 · 1 citationarXiv
A Topological-Framework to Improve Analysis of Machine Learning Model Performance2107.04714v1 · Henry Kvinge, Colby Wight, Sarah Akers et al.2021 · 0 citationsarXiv
Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions2106.04009v1 · Scott Mahan, Henry Kvinge, Tim Doster2021 · 0 citationsarXiv
One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations2106.01423v1 · Henry Kvinge, Scott Howland, Nico Courts et al.2021 · 1 citationarXiv
Hypergraph models of biological networks to identify genes critical to pathogenic viral response.34051754 · Feng, Song, Heath, Emily, Jefferson, Brett et al.2021 · 130 citationsBMC bioinformatics. 2021;22(1):287
Sheaves as a Framework for Understanding and Interpreting Model Fit2105.10414v1 · Henry Kvinge, Brett Jefferson, Cliff Joslyn et al.2021 · 3 citationsarXiv
Prototypical Region Proposal Networks for Few-Shot Localization and Classification2104.03496v1 · Elliott Skomski, Aaron Tuor, Andrew Avila et al.2021 · 0 citationsarXiv
Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning2009.11253v1 · Henry Kvinge, Zachary New, Nico Courts et al.2020 · 1 citationarXiv
Mathematical methods for visualization and anomaly detection in telemetry datasets.31897295 · Aminian, Manuchehr, Andrews-Polymenis, Helene, Gupta, Jyotsana et al.2021 · 5 citationsInterface focus. 2020;10(1):20190086
More chemical detection through less sampling: amplifying chemical signals in hyperspectral data cubes through compressive sensing1906.11818v1 · Henry Kvinge, Elin Farnell, Julia R. Dupuis et al.2019 · 0 citationsarXiv
Career total: 98 works. 63 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.