BinaryPC uses binary principal components of keys to pick the most relevant tokens for attention, preserving accuracy with a 2% budget.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Training-Free Hashing-Based Attention via Binary Principal Components
BinaryPC uses binary principal components of keys to pick the most relevant tokens for attention, preserving accuracy with a 2% budget.