Signals 4 · free daily AI digest

OmniKVQuant: KV Cache Quantization for Omni-LLMs

Paper recorded by Signals 4 on 2026-09-10 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11

Category: cs.CV · 计算机视觉 · first seen 2026-09-11

Abstract

As Omni-modal large language models (Omni-LLMs) take in audio, video and text together, their KV cache memory cost grows. KV cache quantization is the de facto approach in text-only LLMs, but its application to Omni-LLMs remains unexplored. In this paper, we analyze how TurboQuant, a representative rotation-based KV cache quantization method, behaves on multimodal caches and identify two critical

Read on arXiv →

#92 most recent of 237 cs.CV papers we have recorded · ↑ newer: MMGait: Benchmarking and Unifying Gait Recognition across Heterogeneou · ↓ older: Learn the Solid, Not the File: Canonical Inputs for Neural Networks on
Cite this page: OmniKVQuant: KV Cache Quantization for Omni-LLMs: the #92 most recent of 237 cs.CV papers we have recorded (as of 2026-09-10). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/omnikvquant-kv-cache-quantization-for-omni-llms.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV 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