Simple linear attention language models balance the recall-throughput tradeoff (Based)
paper
Fields
id
sources/pap-arch-2402-18668Publisher
arXiv
Kind
paper
Published
2024-02-28
Accessed
2026-10-03
notes
ICLR 2024. Title on arXiv is 'Simple linear attention language models balance the recall-throughput tradeoff'; the model is called Based.
Notes
ICLR 2024. Title on arXiv is 'Simple linear attention language models balance the recall-throughput tradeoff'; the model is called Based.
Cross-references
This record references no other records.