arXiv AI By Munsik Kim

Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression

Read the original on arXiv AI →

arXiv:2605. 25085v2 Announce Type: replace-cross Abstract: We study the rate-distortion limits of online KV cache compression in autoregressive language models, formulating it as sequential Wyner-Ziv source coding on the filtration induced by the model, with the next-step query as decoder side information.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jul 14

Context by Distinct Information: An Auditable Dirichlet-Process Working Memory for Long, Redundant Context Streams

arXiv:2607. 10441v1 Announce Type: cross Abstract: Context engineering decides what information a model carries forward, and current designs meter it in tokens: compressing the past into a bounded recurrent state, keeping a key-value entry for every token, or imposing a fixed budget through a window or eviction rule.

By Siddharth Pal, Viktoria Rojkova