Research scientist on Ferret and MM1 at Apple
Public work celebrated here · current
Haotian co-authored Ferret, the multimodal LLM that can refer to and ground anything in an image at any granularity, and contributed to the MM1 pre-training series. His publicly released research gives app developers a preview of what visual intelligence on device becomes.
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.