Zhilin Yang
Co-first author of XLNet and Transformer-XL; earlier worked at Google Brain and Meta AI
Zhilin Yang completed a PhD in 2019 at the School of Computer Science at Carnegie Mellon University, advised by Ruslan Salakhutdinov and William W. Cohen, and has worked at Google Brain with Quoc V. Le and at Meta AI with Jason Weston. With Zihang Dai, Yang is co-first author of Transformer-XL (2019), an attentive language model that goes beyond a fixed-length context, and of XLNet (2019), a generalized autoregressive pretraining method that integrates ideas from Transformer-XL; both repositories publish code and pretrained models under the Apache 2.0 license. Yang's homepage says Yang is working on a startup.13467
Work
XLNet (external site: github.com)Open-source code
Co-first author with Zihang Dai of "XLNet: Generalized Autoregressive Pretraining for Language Understanding" (2019). The Apache-2.0 repository released the code with XLNet-Large and XLNet-Base pretrained models.345
Transformer-XL (external site: github.com)Open-source code
Co-first author with Zihang Dai of "Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context" (2019). The Apache-2.0 repository under Yang's GitHub account provides PyTorch and TensorFlow code and pretrained TensorFlow models.6782
Other documented roles
Roles the sources document but that are not confirmed as current.
- Worked at Google Brain with Quoc V. Le, Google Brain1
- Worked at Meta AI with Jason Weston, Meta AI1
- PhD student, School of Computer Science (PhD 2019, advised by Ruslan Salakhutdinov and William W. Cohen), Carnegie Mellon University1
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.