1
Knowledge Offloading: Decomposing LLMs into Sparse Backbones and Memory Modules
将LLM分解为稀疏主干+外部记忆模块，探索知识分离存储新范式。
arXiv:2605.29075v1 Announce Type: new Abstract: LLMs encode both general capabilities and domain-specific knowledge in a single set of parameters. We …