MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper
โข
2601.07832
โข
Published
โข
40
Lockinwize Lolite
mzwing
AI & ML interests
Chat AI, Drawing AI
Recent Activity
upvoted
a
paper
3 days ago
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
liked
a model
3 days ago
DAGroup-PKU/MHLA
liked
a model
19 days ago
MiniMaxAI/MiniMax-M2.1
Organizations
upvoted
a
paper
3 days ago