Kimi’s MoE lineage may trace back to Yang Zhilin’s decade-old XLNet PhD work
FinanceYF5 · x · 2026-07-21
The post argues that one key technical source behind Kimi’s success may be founder Yang Zhilin’s PhD work from a decade ago.
Background
- Yang is 34, studied at Tsinghua and CMU, and spent his PhD years at Meta AI and Google Brain.
- His widely cited XLNet paper has reportedly been cited more than 10,000 times.
Claim
- The poster suggests the ideas behind XLNet later evolved into the trillion-parameter MoE architecture used by Kimi K2.
- In other words, the model’s architecture lineage may trace back to a long research path rather than a sudden product breakthrough.
Related event: Kimi's MoE Architecture Traced Back to Yang Zhilin's Decade-Old PhD Thesis(3 posts)→
More from Companies & People
- Sunday Robotics Hires Strategic Projects Lead to Accelerate Home Robots — tonyzzhao · 2026-07-22
- Meta is using AI to help ban accounts on Facebook and Instagram — sbulaev · 2026-07-22
- Apollo Cuts AI Assistant Skill Dev Time by 85% with Deep Agents — LangChain · 2026-07-22
- OpenAI appears to open an “Advertise in ChatGPT” page — montecarl · 2026-07-22
- Apple is now competing directly for creativity app users — speckx · 2026-07-22
- FactoryAI gave back its first millions, then shipped Droid CLI two years later — matanSF · 2026-07-22