Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning Paper • 2510.19338 • Published 6 days ago • 97
view article Article Ring-flash-linear-2.0: A Highly Efficient Hybrid Architecture for Test-Time Scaling By RichardBian and 8 others • 19 days ago • 10
Ovis: Structural Embedding Alignment for Multimodal Large Language Model Paper • 2405.20797 • Published May 31, 2024 • 30