Delve into the cutting edge of Artificial Intelligence with our dedicated Research Paper section.
![[2401.02058] Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Feature Model](http://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png "[2401.02058] Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Feature Model"){kind=logo}
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.…
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees Jonathan Brophy, Zayd Hammoudeh, Daniel Lowd; 24(154):1−48, 2023. Abstract Influence estimation analyzes how changes to the training data can lead to different model predictions; this analysis can help us better understand…
Precisely perceiving the geometric and semantic properties of real-world 3D objects is crucial for the continued evolution of augmented reality and robotic applications. To this end, we present \algfull{} (\algname{}), which incorporates vision-language embeddings of foundation models into 3D Gaussian…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.…
While alignment algorithms are now commonly used to tune pre-trained language models towards a user’s preferences, we lack explanations for the underlying mechanisms in which models become “aligned”, thus making it difficult to explain phenomena like jailbreaks. In this work…
[Submitted on 3 Jan 2024] Download a PDF of the paper titled Hierarchical Clustering in ${\Lambda}$CDM Cosmologies via Persistence Energy, by Michael Etienne Van Huffel and 2 other authors Download PDF HTML (experimental) Abstract:In this research, we investigate the structural…
Small Transformers Compute Universal Metric Embeddings Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanić; 24(170):1−48, 2023. Abstract We study representations of data from an arbitrary metric space $\mathcal{X}$ in the space of univariate Gaussian mixtures equipped with a transport metric (Delon and…
[Submitted on 3 Jan 2024] Download a PDF of the paper titled Can We Generate Realistic Hands Only Using Convolution?, by Mehran Hosseini and Peyman Hosseini Download PDF Abstract:The enduring inability of image generative models to recreate intricate geometric features,…
This paper presents a reputation-based threat mitigation framework that defends potential security threats in electroencephalogram (EEG) signal classification during model aggregation of Federated Learning. While EEG signal analysis has attracted attention because of the emergence of brain-computer interface (BCI) technology,…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.…