Signals 4 · free daily AI digest

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

Paper recorded by Signals 4 on 2026-09-29 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-29 on arXiv · recorded by Signals 4 on 2026-09-30

Category: cs.LG · 机器学习 · first seen 2026-09-30

Abstract

KV cache memory and bandwidth costs grow with context length and batch size, which limits efficient long-context inference. To address this bottleneck, we introduce WUSH-KV for low-bit KV-cache quantization. It adapts WUSH, which constructs a data-aware transform from the second-order statistics of both factors in a matrix product to reduce quantization error. WUSH-KV uses calibration data to cons

Read on arXiv →

#6 most recent of 334 cs.LG papers we have recorded · ↑ newer: Achieving an $O(1/N)$ Optimality Gap in Average-Reward Weakly-Coupled · ↓ older: ReCIRC: Rectified Conformal Risk Control
Cite this page: WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms: the #6 most recent of 334 cs.LG papers we have recorded (as of 2026-09-29). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/wush-kv-kv-cache-quantization-with-data-adaptive-transforms.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions