Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
Paper
•
2510.19338
•
Published
•
111
Yue Zhang
York-Z
AI & ML interests
None yet
Recent Activity
authored
a paper
28 days ago
Every Attention Matters: An Efficient Hybrid Architecture for
Long-Context Reasoning
liked
a model
28 days ago
inclusionAI/Ring-flash-linear-2.0-128k
updated
a model
28 days ago
inclusionAI/Ring-flash-linear-2.0-128k
Organizations
upvoted
a
paper
28 days ago
upvoted
2
articles
about 1 month ago
Article
Art of Focus: Page-Aware Sparse Attention and Ling 2.0’s Quest for Efficient Context Length Scaling
•
14
Article
Ring-flash-linear-2.0: A Highly Efficient Hybrid Architecture for Test-Time Scaling
•
11