
State-space models offer an efficient alternative to transformers for processing long sequences, achieving competitive results with reduced memory usage.


coremsg

locost-state-space-models-for-long-document-abstractive-summarization


LOCOST: State-Space Models for Long Document Abstractive Summarization


title_rewrite


State-space models offer a low-complexity alternative to transformers for encoding long sequences, enabling efficient handling of significantly longer inputs. LOCOST demonstrates competitive performance while being more memory-efficient than state-of-the-art sparse transformers.
