arxiv
PublishedOctober 3, 2026 at 4:00 AM
—neutral
AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models
Publisher summary· verbatim
arXiv:2610.01395v1 Announce Type: new Abstract: Muon improves large-scale training by applying a spectral-norm steepest-descent update to matrix parameters, but practical models also contain parameter blocks that do not fit dense-matrix geometry. One important case is the tied vocabulary table, whic
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSequential Capacity of Quantum Processes with Finite Memory1darxivGraph Representation via Elements of Discrete Morse and Cobordism Theories1darxivDo Your Own Research: Learning to Forecast by Learning to Search1darxivFastCI: Efficient GPU-Intensive CI for LLM Training Frameworks1dThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗