Leads post-training for Apple Foundation Models
Public work celebrated here · current
Zirui leads post-training for the Apple Foundation Models and co-authored MM1, after earlier landmark work on CoCa and SimVLM at Google Brain. The instruction-following polish people feel in on-device intelligence is the craft he works on in public view.
We built this from your public work because we think it deserves celebrating. You did not ask us to, so the only fair thing is that you decide what happens to it. Claim it and it is yours to edit. Ask us to change something and we will. Ask us to take it down and it is gone within 72 hours — free, no account needed, and nobody will try to talk you out of it.