Niki Parmar
Co-author of the Transformer paper and first-listed author of Image Transformer, both from Google
Niki Parmar is a co-author of Attention Is All You Need (2017), listed there with a Google Research affiliation; the paper's contribution note says Parmar designed, implemented, tuned, and evaluated many model variants in the original codebase and in Tensor2Tensor. Parmar is the first-listed author, with equal contribution from Ashish Vaswani and a Google Brain affiliation, of Image Transformer (2018), which extends the self-attention architecture to image generation, and is a co-author of the 2018 Tensor2Tensor paper.123
Work
Transformer (Attention Is All You Need) (external site: arxiv.org)Published research
Co-author of the 2017 paper that introduced the Transformer; the contribution note says Parmar designed, implemented, tuned, and evaluated model variants in the original codebase and in Tensor2Tensor.1
Image Transformer (external site: arxiv.org)Published research
Co-first author (with Ashish Vaswani, order by coin flip) of the 2018 paper that applies self-attention restricted to local neighborhoods to autoregressive image generation.2
Tensor2Tensor (external site: github.com)Open-source code
Co-author of the 2018 Tensor2Tensor paper; the Apache-2.0 library, developed by the Google Brain team, includes the reference implementation of the Transformer.34
Other documented roles
Roles the sources document but that are not confirmed as current.
- Listed with Google Research (2017) and Google Brain (2018) affiliations on papers, Google Research and Google Brain123
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.