conftrace_

recurrent compression

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

long-form context (1) query-dependent modeling (1) key-value pair (1) large language model (1) memory compression (1) context injection (1) long context (1) hierarchical memory (1) context window (1) efficient inference (1)

Papers

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs NAACL 2025 MELODI: Exploring Memory Compression for Long Contexts ICLR 2025