7 papers
VASAE: Naming SAE Dictionary Directions with Vocabulary-Aligned Anchoring
Kairui Zhang, Ziwen Yu, Zahraa S. Abdallah +1
Sparse autoencoders (SAEs) provide useful decompositions of Transformer residual streams, but their learned features are usually named post hoc rather than directly connected to th…
KnowEEG: Explainable Knowledge Driven EEG Classification
Amarpal Sahota, Navid Mohammadi Foumani, Raul Santos-Rodriguez +1
Electroencephalography (EEG) is a method of recording brain activity that shows significant promise in applications ranging from disease classification to emotion detection and bra…
A Regime-Aware Fusion Framework for Time Series Classification
Honey Singh Chauhan, Zahraa S. Abdallah
Kernel-based methods such as Rocket are among the most effective default approaches for univariate time series classification (TSC), yet they do not perform equally well across all…
Establishing Validity for Distance Functions and Internal Clustering Validity Indices in Correlation Space
Isabella Degen, Zahraa S Abdallah, Kate Robson Brown +1
Internal clustering validity indices (ICVIs) assess clustering quality without ground truth labels. Comparative studies consistently find that no single ICVI outperforms others acr…
Towards deployment-centric multimodal AI beyond vision and language
Xianyuan Liu, Jiayang Zhang, Shuo Zhou +45
Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as h…
CSTS: A Benchmark for the Discovery of Correlation Structures in Time Series Clustering
Isabella Degen, Zahraa S Abdallah, Henry W J Reeve +1
Time series clustering promises to uncover hidden structural patterns in data with applications across healthcare, finance, industrial systems, and other critical domains. However,…