🤫husshhussh
🤫husshhusshOnePuppy
🤫 celebrates

Pierre Ablin

Machine learning researcher at Apple MLR Paris

EngineeringiOSmacOS
The work

What we are celebrating, specifically.

  • Sigmoid self-attention theory (ICLR 2025)
  • Scaling Laws for Optimal Data Mixtures
  • Fast optimization algorithms research

Apple

Machine Learning Researcher, MLR Paris · current

Why

Why we celebrate them.

Pierre brings serious optimization theory to the practical questions of training foundation models, and mentors students while doing it. His proofs that sigmoid attention transformers are universal approximators gave a speedup a solid mathematical floor.

Sources — their own pages, so you can check us

  • Personal site
  • Google Scholar
This page is yours

Pierre Ablin, this belongs to you.

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.

Claim or remove this pageEveryone we celebrate