Efficient Pre-Training with Token Superposition
Paper • 2605.06546 • Published • 48 •
8
Adam Klein
aklein4
·
AI & ML interests
None yet
Recent Activity
published a model about 7 hours ago
aklein4/ZEBRA-v2_360m-cauchy updated a model about 13 hours ago
aklein4/ZEBRA-v2_1p7b-fixed published a model about 17 hours ago
aklein4/ZEBRA-v2_1p7b-fixedOrganizations
None yet
commented a
paper 2 months ago