MMODELYST
People/Hongtao Zhang
PPL

Hongtao Zhang

Papers (3)
The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-trainingExtra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-TrainingWhen and Why Grouping Attention Heads Accelerates Muon Optimization