Repeat After Me: Transformers are Better than State Space Models at Copying
Paper
•
2402.01032
•
Published
•
25
State Space Models
-
-
Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
Paper • 2402.04248 • Published • 33 -
Linear Transformers with Learnable Kernel Functions are Better In-Context Models
Paper • 2402.10644 • Published • 82 -
In Search of Needles in a 10M Haystack: Recurrent Memory Finds What LLMs Miss
Paper • 2402.10790 • Published • 43 -
DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models
Paper • 2403.00818 • Published • 20