10 citations · 11 across the 5 of their papers we have counts for
3 papers · 1 filter
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
Junhyuck Kim, Jongho Park, Jaewoong Cho +1
We introduce Lexico, a novel KV cache compression method that leverages sparse coding with a universal dictionary. Our key finding is that key-value cache in modern LLMs can be acc…
Task Diversity Shortens the ICL Plateau
Jaeyeon Kim, Sehyun Kwon, Joo Young Choi +4
In-context learning (ICL) describes a language model's ability to generate outputs based on a set of input demonstrations and a subsequent query. To understand this remarkable capa…
Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
Jongho Park, Jaeseung Park, Zheyang Xiong +5
State-space models (SSMs), such as Mamba (Gu & Dao, 2023), have been proposed as alternatives to Transformer networks in language modeling, by incorporating gating, convolutions, a…