@stanfordnlp: Many roughly know how a transformer works To REALLY understand modern neural LMs—MoEs, GPU tiling, kernels, RLHF, data—…

X AI KOLs Following News

Summary

Stanford's CS336 course on modern neural language models, covering topics like MoEs and RLHF, is being released on YouTube with a two-week delay.

Many roughly know how a transformer works To REALLY understand modern neural LMs—MoEs, GPU tiling, kernels, RLHF, data—you need CS336 By @tatsu_hashimoto, @percyliang The 2026 edition appears on yt with ~2 weeks delay http://youtube.com/playlist?list=PLoROMvodv4rMqXOcazWaTUHhq-yembLCV… Materials https://cs336.stanford.edu
Original Article
View Cached Full Text

Cached at: 05/13/26, 12:32 AM

Many roughly know how a transformer works To REALLY understand modern neural LMs—MoEs, GPU tiling, kernels, RLHF, data—you need CS336 By @tatsu_hashimoto, @percyliang The 2026 edition appears on yt with ~2 weeks delay http://youtube.com/playlist?list=PLoROMvodv4rMqXOcazWaTUHhq-yembLCV… Materials https://cs336.stanford.edu


@stanfordnlp: Many roughly know how a transformer works To REALLY understand modern neural LMs—MoEs, GPU tiling, kernels, RLHF, data—…

Channel: @stanfordnlp Source: https://www.youtube.com/playlist?list=PLoROMvodv4rMqXOcazWaTUHhq-yembLCV

Similar Articles