DyT (LayerNorm removal) composition study. arXiv 2604.23434.
Lucky Verma
lucky-verma
AI & ML interests
None yet
Recent Activity
updated a dataset 9 days ago
lucky-verma/grokking-diagnostics-runs published a dataset 16 days ago
lucky-verma/grokking-diagnostics-runs updated a collection 17 days ago
Archived ML PapersOrganizations
None yet