Yi Tay
Documenting my 3.3 years at Google Research and Brain. Releasing the new open source Flan-UL2 20B model. Here are some of the best language AI / NLP papers of 2022! Some thoughts on emergent abilities and scaling language models. Made with Squarespace
Hello. I am a scientist & engineer at Google DeepMind. I am on the Gemini core team working on RL & post-training. Recently, I was model co-lead & co-captain of the Gemini Deep Think model that achieved the historic IMO Gold Medal 🥇. Previously, I co-led early LLM efforts at Google Brain including PaLM-2, UL2 and Flan-2. While I was a researcher for most of my professional life, I also took a short break to be a co-founder of a "unicorn" AI startup in 2023-2024. As a side quest, in 2025, I help built and co-founded GDM Singapore together with Quoc Le. I currently lead the Singapore…
saved by
related reading
- Training great LLMs entirely from ground up in the wilderness as a startup - Yi Tayyitay.net
- Jason Weijasonwei.net
- Vincent Huangvvhuang.com
- Non_Interactive – Software & MLnonint.com
- Ai2: Truly open breakthrough AIallenai.org
- Lil'Loglilianweng.github.io
- Thoughts — Jason Weijasonwei.net
- Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com
- Explore | alphaXivalphaxiv.org
- 2025: The year in LLMssimonwillison.net
- LLM Resourcesforrestbicker.com
- What happened to BERT & T5? On Transformer Encoders, PrefixLM and Denoising Objectives - Yi Tayyitay.net