arXiv AI July 14, 2026 By Paolo D'Alberto, Ashish Siarasao, Elliott Delaye, Rajeev Patwari

Ablation, Statistical Inference, and Validation for KV-Cache Compression

arXiv:2607. 09683v1 Announce Type: cross Abstract: This study systematically compares Turbo-Quant and SpectralQuant KV-cache compression, evaluating non-dominated schemes, including WHT rotation with Beta Lloyd-Max and QJL, through a statistical validation methodology that separates systematic codec differences from implementation variance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv AI

Aug 11

KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models

arXiv:2608. 09412v1 Announce Type: new Abstract: KV-cache compression reduces long-context memory, but aggregate task scores reveal neither which correct executions fail nor why.

By Chen Qiu, Ziwu Liu, Chao Fei, Guozhong Li, Panos Kalnis

llms benchmarks

arXiv Machine Learning

Aug 11

SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding

arXiv:2608. 07915v1 Announce Type: new Abstract: Large language models (LLMs) increasingly read long inputs in the agentic era, from whole documents and codebases to conversations across many turns.

By Jiamu Zhang, Liang Wu, Kelly Wan, Hanjie Chen, Liangjie Hong

llms agents efficiency benchmarks

arXiv AI

Jul 24

Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches

arXiv:2607. 20538v1 Announce Type: cross Abstract: Long-context Transformer inference increasingly relies on KV-cache compression or quantization.

By Yitao Jiang, Yaoqing Yang, Luyang Zhao, Muhao Chen, Devin Balkcom

llms efficiency

arXiv Machine Learning

Sep 22

KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation

arXiv:2609.24298v1 Announce Type: new Abstract: What limits KV-cache compression at extreme bit-rates? We argue that it is not the choice of compression scheme, but how its budget is allocated across...

By Sihyeon Ha, Jaeho Lee, Yo-Seb Jeon

efficiency benchmarks

arXiv AI

Jun 16

PolyKV: Heterogeneous Retention and Allocation for KV Cache Compression

arXiv:2606. 15157v1 Announce Type: cross Abstract: KV cache compression is essential for reducing the memory cost of long-context large language model inference.

By Chao Fei, Panos Kalnis

llms efficiency

arXiv AI

Sep 10

Attention-Weighted Value Projection for KV-Cache Compression

arXiv:2604.11501v2 Announce Type: replace-cross Abstract: Rank reduction discards dimensions; quantization keeps them at lower precision. Comparing the two requires a choice of what compression shoul...

By Samuel Salfati

efficiency

One email a morning, machine-written

Related stories

KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models

SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding

Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches

KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation

PolyKV: Heterogeneous Retention and Allocation for KV Cache Compression

Attention-Weighted Value Projection for KV-Cache Compression