@inproceedings{wang-etal-2026-resonating,
title = "Resonating with {R}o{PE}: Spectral Quantization for High-Fidelity Key Cache Compression",
author = "Wang, Xuefei and
Tang, Haoyu and
Liang, Tianyuan and
Wang, Zhibin and
Hu, Yupeng and
Guan, Weili",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1732/",
pages = "37328--37348",
ISBN = "979-8-89176-390-6",
abstract = "The linear growth of KV cache bottlenecks long-context LLMs, yet RoPE-induced oscillations complicate Key cache quantization. To address this issue, we propose SpectrumQuant, a frequency-domain framework that utilizes the Discrete Cosine Transform (DCT) to convert these oscillations into sparse spectral representations. Specifically, our pipeline integrates dominant frequency extraction, hybrid bit-width allocation, and high-frequency pre-emphasis to maximize fidelity while minimizing memory footprint. To eliminate computational overhead, we develop fused Triton kernels featuring deferred inverse transformation and on-chip sparse accumulation. Extensive experiments on several benchmarks confirm SpectrumQuant achieves efficient compression with performance and latency comparable to FP16 baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-resonating">
<titleInfo>
<title>Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuefei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyuan</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhibin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yupeng</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weili</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>The linear growth of KV cache bottlenecks long-context LLMs, yet RoPE-induced oscillations complicate Key cache quantization. To address this issue, we propose SpectrumQuant, a frequency-domain framework that utilizes the Discrete Cosine Transform (DCT) to convert these oscillations into sparse spectral representations. Specifically, our pipeline integrates dominant frequency extraction, hybrid bit-width allocation, and high-frequency pre-emphasis to maximize fidelity while minimizing memory footprint. To eliminate computational overhead, we develop fused Triton kernels featuring deferred inverse transformation and on-chip sparse accumulation. Extensive experiments on several benchmarks confirm SpectrumQuant achieves efficient compression with performance and latency comparable to FP16 baselines.</abstract>
<identifier type="citekey">wang-etal-2026-resonating</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1732/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>37328</start>
<end>37348</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression
%A Wang, Xuefei
%A Tang, Haoyu
%A Liang, Tianyuan
%A Wang, Zhibin
%A Hu, Yupeng
%A Guan, Weili
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wang-etal-2026-resonating
%X The linear growth of KV cache bottlenecks long-context LLMs, yet RoPE-induced oscillations complicate Key cache quantization. To address this issue, we propose SpectrumQuant, a frequency-domain framework that utilizes the Discrete Cosine Transform (DCT) to convert these oscillations into sparse spectral representations. Specifically, our pipeline integrates dominant frequency extraction, hybrid bit-width allocation, and high-frequency pre-emphasis to maximize fidelity while minimizing memory footprint. To eliminate computational overhead, we develop fused Triton kernels featuring deferred inverse transformation and on-chip sparse accumulation. Extensive experiments on several benchmarks confirm SpectrumQuant achieves efficient compression with performance and latency comparable to FP16 baselines.
%U https://aclanthology.org/2026.acl-long.1732/
%P 37328-37348
Markdown (Informal)
[Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression](https://aclanthology.org/2026.acl-long.1732/) (Wang et al., ACL 2026)
ACL