2 papers
cs.CL2025
RMem: Bridging Memory Retention and Retrieval via Reversible Compression
Xiaoqiang Wang, Suyuchen Wang, Yun Zhu +1
Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external stora…
cs.CL2024
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Zhiyuan Hu, Yuliang Liu, Jinman Zhao +8
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts t…