註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Evolving Machines
@evolvymachines
Continuous evaluation infrastructure for self-improving agents.
加入 January 2026
0 正在關注    210 粉絲
Scaling matrix optimizers to wide networks is expensive. Our new research post introduces Echelon, a rank-anchored formulation of Muon that orthogonalizes only the top subspace in O(mnr) time while rescaling the tail: up to 10.5× faster optimizer steps, with Muon's loss at 1.3B. Blog: We pair the algorithm with the first Lean-checked convergence proof for spectral steepest descent. Lean proofs:
顯示更多
0
15
315
42
轉發到社區