Everyone is talking about Kimi K3, but if you jump straight into the technical report, you’ll quickly realize it’s standing on years of research -- just like any breakthrough is! If you want to understand the work put into it by the Kimi team, here’s the reading order I’d recommend. Linear Transformers Are Secretly Fast Weight Programmers This is the foundation. The paper provides one of the most influential interpretations of linear attention, showing that many linear attention mech...