Collection by
Mar 4
Mar 4
-
Transformers are Multi-State RNNs
Paper • 2401.06104 • Published • 34 -
Linear Transformers with Learnable Kernel Functions are Better In-Context Models
Paper • 2402.10644 • Published • 74 -
In Search of Needles in a 10M Haystack: Recurrent Memory Finds What LLMs Miss
Paper • 2402.10790 • Published • 40 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 571
