Linear-Time Context Compression with State-Space Encoding
arXiv:2610.33006v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) impose substantial computation and memory costs as context sizes increase, motivating methods that compress a context into a shorter representation before inference. Existing soft-prompt compression metho…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-27 04:00 · arXiv cs.CL
Linear-Time Context Compression with State-Space Encoding