About Me
I am Yi Shen (in Chinese: 沈 毅), currently a researcher in OpenAI.
I led or co-led the development of the following models:
- Advanced Voice Mode (speech-to-speech model).
- Text-to-speech: gpt-4o-mini-tts
- Speech-to-text: gpt-4o-transcribe, gpt-4o-mini-transcribe
Previously…
I was a senior staff tech lead manager in Waymo, leading Waymo’s Scene Understanding team.
I also worked for Nuro and Google.
I received my PhD degree in Computer Science from University of North Carolina at Charlotte, and Bachelor’s degree from Fudan University.
I’m proud of several exciting experiences, from the most recent to the earliest:
- Trained ChatGPT’s speech-to-speech models and grew the DAU from 0 to XX millions.
- Led an elite team in Waymo to solve long-tail issues to enable dense urban autonomous driving.
- Established Nuro’s software stack from ground-up.
- Trained and deployed Google’s first deep learning-based image embedding.
- Won silver medal on ACM/ICPC world final (6th place overall).
In my spare time, I enjoy photography, sports and reading.