AIStanford course to focus on efficient language models in fall 2026
An instructor says MS&E 319 will examine how to choose training objectives, model architectures and inference algorithms for a given modeling goal and limited compute budget.
TLDR
An instructor announced Stanford’s MS&E 319: Efficient Generative Language Models for fall 2026. Planned topics include efficient pre-training, mixture-of-experts architectures, attention and KV-cache compression, quantization and distillation. The teaching team will try to post all lecture materials and recordings as the course unfolds.
Combined views
7.8K
1 Source, first seen 5h ago
Stanford course to focus on efficient language models in fall 2026
An instructor says MS&E 319 will examine how to choose training objectives, model architectures and inference algorithms for a given modeling goal and limited compute budget.
TLDR
An instructor announced Stanford’s MS&E 319: Efficient Generative Language Models for fall 2026. Planned topics include efficient pre-training, mixture-of-experts architectures, attention and KV-cache compression, quantization and distillation. The teaching team will try to post all lecture materials and recordings as the course unfolds.