Hamming Attention Distillation binarizes transformer keys and queries to +1/-1 and prunes attention to the top N links, reporting single-point accuracy losses and large simulated hardware savings.
On a model of associative memory with huge storage capacity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Hamming Attention Distillation: Binarizing Keys and Queries for Efficient Long-Context Transformers
Hamming Attention Distillation binarizes transformer keys and queries to +1/-1 and prunes attention to the top N links, reporting single-point accuracy losses and large simulated hardware savings.