Futurologist@futurology.today to Futurology@futurology.todayEnglish · edit-25 days agoByte Latent Transformer: Patches Scale Better Than Tokens: an important 1st step away from the standard Transformer model that's dominated much of AI research since it was invented at Google in 2017 ?ai.meta.comexternal-linkmessage-square1fedilinkarrow-up112arrow-down10
arrow-up112arrow-down1external-linkByte Latent Transformer: Patches Scale Better Than Tokens: an important 1st step away from the standard Transformer model that's dominated much of AI research since it was invented at Google in 2017 ?ai.meta.comFuturologist@futurology.today to Futurology@futurology.todayEnglish · edit-25 days agomessage-square1fedilink