SLA2: Sparse-Linear Attention with Learnable Routing and QAT
Paper
•
2602.12675
•
Published
•
45
ShaoXuan Xu
WriteMath
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
SLA2: Sparse-Linear Attention with Learnable Routing and QAT
upvoted
a
paper
3 months ago
UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers
updated
a dataset
8 months ago
WriteMath/BalanceBench
Organizations
None yet
upvoted
a
paper
1 day ago