A pre-trained PFN transformer is prompted with a few labeled samples to cluster the rest of a dataset by attention, with theoretical and empirical claims that are not fully supported.
Mathematical classification and clustering, volume 11
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Clustering by Attention: Leveraging Prior Fitted Transformers for Data Partitioning
A pre-trained PFN transformer is prompted with a few labeled samples to cluster the rest of a dataset by attention, with theoretical and empirical claims that are not fully supported.