ResKV: Reconstructing Omitted Attention Contributions for Fixed-Budget KV Cache Compression
Yuhang Zhan, Lisi Chen, Shuo Shang
cs.CL
Submitted: 2026-07-31
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Llama 3 Herd of Models
- KVSculpt: KV Cache Compression as Distillation
- Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
- Qwen2.5 Technical Report
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering