Meta
Google Brain
Tsinghua University
Carnegie Mellon University
Wu YuxinCo-founder and Member of Technical Staff · Moonshot AIResearcher↗
Researcher · Founder
Yang Zhilin
Moonshot AICo-founder
Yang helped language models make sense of longer passages. He co-developed Transformer-XL, which carries information across segments of text,[1] and XLNet, which learns from words on both sides of a prediction.[2] He co-founded Moonshot AI, whose open-weight Kimi K2 can write code and use software tools.[3]
Career & education
Current roleMoonshot AI2023-presentCo-founder
Moonshot AI2023-presentPreviously
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations55,827As of Nov 13, '26
citations+5,584Since last snapshot, Jun 15, '26
Selected contributions
XLNet: Generalized Autoregressive Pretraining for Language Understanding
XLNet learns language context by predicting words in varied orders.
References
- Transformer-XLarxiv.org
Yang and his co-authors describe how reusing information from earlier segments lets the model learn longer-range relationships.
- XLNetarxiv.org
Yang and his co-authors train the model with varied prediction orders so it can learn from context on both sides.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 24, 2026 · Checked for accuracy and new information.