arxiv
PublishedApril 21, 2026 at 4:00 AM
▲bullish
Sequential KV Cache Compression via Probabilistic Language Tries: Beyond the Per-Vector Shannon Limit
Publisher summary· verbatim
arXiv:2604.15356v1 Announce Type: cross Abstract: Recent work on KV cache quantization, culminating in TurboQuant, has approached the Shannon entropy limit for per-vector compression of transformer key-value caches. We observe that this limit applies to a strictly weaker problem than the one that ac
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivTeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents2harxivAmbient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision2harxivMonadic Second-Order Logic in HOL: Deep and Shallow with Automated Faithfulness (Extended Preprint)2harxivNatural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation2hThe Bubble Brief
WEEKLYRead compression insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗