MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper
•
2601.07832
•
Published
•
37
Hallucinatie Hou
Hallucinatie
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
upvoted
a
paper
8 months ago
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
Organizations
None yet
upvoted
a
paper
1 day ago