作者位次 #3/8ACL 2026Findings· Findings of ACL
From 128 K to 4 M : Efficient Training of Ultra-Long Context Large Language Models
Chejian Xu · Wei Ping · Peng Xu · Zihan Liu · Boxin Wang · Mohammad Shoeybi · Bo Li · Bryan Catanzaro
摘要
Long-context capabilities are essential for a wide range of applications, including document and video understanding, in-context learning, and inference-time scaling, all of which require models to process and reason over long sequences of text and multimodal data. In this work, we introduce an e...