MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper
โข
2601.07832
โข
Published
โข
51
Lockinwize Lolite
mzwing
AI & ML interests
Chat AI, Drawing AI
Recent Activity
upvoted
a
paper
14 days ago
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
liked
a model
14 days ago
DAGroup-PKU/MHLA
liked
a model
about 1 month ago
MiniMaxAI/MiniMax-M2.1
Organizations
upvoted
a
paper
14 days ago