most citedPredicting the Past: Estimating Historical Appraisals with OCR and Machine Learning

3 citations · 4 across the 2 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2024★ 1 cited

EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance

Yingxin Li, Ye Li, Yuan Meng +4

As large language models (LLMs) continue to advance, the demand for higher quality and faster processing of long contexts across various applications is growing. KV cache is widely…