E^2-LLM: Efficient and Extreme Length Extension of Large Language Models
Paper
•
2401.06951
•
Published
•
24
long context LLM
-
-
Extending LLMs' Context Window with 100 Samples
Paper • 2401.07004 • Published • 14 -
Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon
Paper • 2401.03462 • Published • 26 -
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry
Paper • 2402.04347 • Published • 13 -
LongAlign: A Recipe for Long Context Alignment of Large Language Models
Paper • 2401.18058 • Published • 21