作者位次 #3/7ACL 2026Findings· Findings of ACL
From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models
Junlong Tong · Zilong Wang · YuJie Ren · Peiran Yin · Hao Wu · Wei Zhang · Xiaoyu Shen
摘要
Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in dynamic, real-time scenarios. To address this gap, the streaming LLM paradigm has emerged. However, existing definitions of streaming LLMs remain frag...