Muon-style optimizers take a matrix-valued momentum or preconditioned update $B = U \operatorname{diag}(σ_1,\ldots,σ_r) V^\top$ and replace it with its canonical partial polar factor...
You can contact @luiz3244 right away.
10 likes. "[4K] 십센치(10CM, 권정열) '지금 우리 사이는' 세로 직캠 @MU:CON 2025(뮤콘, MUCON), 250913"