PRISM forms predictions as sparse mixtures of learned prototypes trained with clustering objectives, matching dense model accuracy while enabling ~500x faster data attribution and behavior editing without finetuning.
Proceedings of the 34th International Conference on Machine Learning , pages =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Diverse language models converge on similar periodic number features with a two-tier hierarchy of Fourier sparsity and geometric separability, acquired via language co-occurrences or multi-token arithmetic.
citing papers explorer
-
Convergent Evolution: How Different Language Models Learn Similar Number Representations
Diverse language models converge on similar periodic number features with a two-tier hierarchy of Fourier sparsity and geometric separability, acquired via language co-occurrences or multi-token arithmetic.