RACE Attention is a strictly linear-time attention mechanism that approximates softmax attention outputs using Gaussian projections and soft LSH to enable training on contexts up to 12 million tokens.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A system counts individuals via face-derived anonymous identifiers in encrypted Bloom filters, enabling cross-location tracking without identity disclosure.
citing papers explorer
-
RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts
RACE Attention is a strictly linear-time attention mechanism that approximates softmax attention outputs using Gaussian projections and soft LSH to enable training on contexts up to 12 million tokens.
-
Head Count: Privacy-Preserving Face-Based Crowd Monitoring
A system counts individuals via face-derived anonymous identifiers in encrypted Bloom filters, enabling cross-location tracking without identity disclosure.