Simple linear attention language models balance the recall-throughput tradeoff — mentioned by korbip

Sat, 15 Feb 2025 03:04:16 GMT

There is a LOT of effort in the research community currently: 1. Improving the Self-Attention in the Transformer as is, keeping the quadratic complexity, which has some theoretical advantage in principle[1]: The most hyped one probably DeepSeek's Multi-Latent Attention[15], which kind of is Attention still - but also somehow different. 2. Linear RNNs: This starts from Linear Attention[2], DeltaNet[3], RKWV[4], Retention[5], Gated Linear Attention[6], Mamba[7], Griffin[8], Based[9], xLSTM[10], TTT[11], Gated DeltaNet[12], Titans[13]. They all have an update like: C_{t} = F_{t} C_{t-1} + i_{t}…

Paper and discussion history. A mention is not an endorsement.

Simple linear attention language models balance the recall-throughput tradeoff — mentioned by f_devd

Fri, 04 Oct 2024 00:49:41 GMT

Transformers actually have an quantifiable state size (see https://hazyresearch.stanford.edu/static/posts/2024-06-22-ac...) although it's anywhere between 200k and 2M floats (for 360M and 1.33B respectively iinm). So a sufficiently sized RNN could have the same state capacity as a transformer. (this is from the Based paper: https://arxiv.org/pdf/2402.18668)

Paper and discussion history. A mention is not an endorsement.

Simple linear attention language models balance the recall-throughput tradeoff · HackerPapers discussions

Simple linear attention language models balance the recall-throughput tradeoff — mentioned by korbip

Simple linear attention language models balance the recall-throughput tradeoff — mentioned by f_devd