E^2-LLM: Efficient and Extreme Length Extension of Large Language Models
Paper
•
2401.06951
•
Published
•
25
Long Context
-
-
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
Paper • 2401.01325 • Published • 27 -
Extending LLMs' Context Window with 100 Samples
Paper • 2401.07004 • Published • 15 -
LongAlign: A Recipe for Long Context Alignment of Large Language Models
Paper • 2401.18058 • Published • 20 -
In Search of Needles in a 10M Haystack: Recurrent Memory Finds What LLMs Miss
Paper • 2402.10790 • Published • 41 -
SCBench: A KV Cache-Centric Analysis of Long-Context Methods
Paper • 2412.10319 • Published • 9