collaborators

1 paper

cs.AI2026

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

Chen Qiu, Ziwu Liu, Chao Fei +2

KV-cache compression reduces long-context memory, but aggregate task scores reveal neither which correct executions fail nor why. We present KVDiagnosis, a diagnostic dataset and b…