🛰️ Daily AI Frontier
‹ back to 2026-08-17

KV Cache Compression Through the Lens of Transform Coding

Research Efficiency & Systems

Ranking

Overall 82
Content 100
Popularity 41

Observed public metrics from 1 member.

Merged summary

TL;DR - Attention-Aware Transform Coding compresses LLM KV caches by optimizing bit allocation for attention-level distortion rather than cache reconstruction error. It achieves near-lossless accuracy at roughly 5.8Ă— compression across two instruction-tuned models and several benchmarks.

  • Derives additive key and value distortion terms that factor across tokens and channels under a white-noise quantization model.
  • Uses transform coding and reverse water-filling to allocate bits based on calibration data.
  • Evaluated on Llama-3.1-8B-Instruct and Qwen-2.5-7B-Instruct across long-context, reasoning, and knowledge benchmarks.
  • Unlike the reported baselines, AATC avoids notable degradation across the tested settings.

Sources (1)

KV Cache Compression Through the Lens of Transform Coding

arXiv cs.LG Hannah Laus, Claudio Mayrink Verdun, Hao Wang, Flavio du Pin Calmon, Felix Krahmer 2026-08-14 arXiv:2608.14191
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-12 14:25:57.523083 UTC

TL;DR - Attention-Aware Transform Coding compresses LLM KV caches by optimizing bit allocation for attention-level distortion rather than cache reconstruction error. It achieves near-lossless accuracy at roughly 5.8Ă— compression across two instruction-tuned models and several benchmarks.

  • Derives additive key and value distortion terms that factor across tokens and channels under a white-noise quantization model.
  • Uses transform coding and reverse water-filling to allocate bits based on calibration data.
  • Evaluated on Llama-3.1-8B-Instruct and Qwen-2.5-7B-Instruct across long-context, reasoning, and knowledge benchmarks.
  • Unlike the reported baselines, AATC avoids notable degradation across the tested settings.
item →