7 papers
KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction
Aomufei Yuan, Zhiming Wang, Ruijie Miao +8
As the context length of current large language models (LLMs) rapidly increases, the memory demand for the Key-Value (KV) cache is becoming a bottleneck for LLM deployment and batc…
MagnifierSketch: Quantile Estimation Centered at One Point
Jiarui Guo, Qiushi Lyu, Yuhan Wu +6
In this paper, we take into consideration quantile estimation in data stream models, where every item in the data stream is a key-value pair. Researchers sometimes aim to estimate…
ScholarSearch: Benchmarking Scholar Searching Ability of LLMs
Junting Zhou, Wang Li, Yiyan Liao +5
Large Language Models (LLMs)' search capabilities have garnered significant attention. Existing benchmarks, such as OpenAI's BrowseComp, primarily focus on general search scenarios…
Detecting Flow Gaps in Data Streams
Siyuan Dong, Yuxuan Tian, Wenhan Ma +5
Data stream monitoring is a crucial task which has a wide range of applications. The majority of existing research in this area can be broadly classified into two types, monitoring…
ResidualSketch: Enhancing Layer Efficiency and Error Reduction in Hierarchical Heavy Hitter Detection with ResNet Innovations
Xilai Liu, Yuxuan Tian, Xiangyuan Wang +4
In network management, swiftly and accurately identifying traffic anomalies, including Distributed Denial-of-Service (DDoS) attacks and unexpected network disruptions, is essential…
Hidden Sketch: A Space-Efficient Reversible Sketch for Tracking Frequent Items in Data Streams
Zicang Xu, Yuxuan Tian, Yuhan Wu +1
Modern data stream applications demand memory-efficient solutions for accurately tracking frequent items, such as heavy hitters and heavy changers, under strict resource constraint…