Publications (11)
Final assessment of radioactive impurities in the JUNO detector
Thomas Adam, Fengpeng An, Costas Andreopoulos +569
The Jiangmen Underground Neutrino Observatory (JUNO) collaboration has completed the construction of the 20,000-ton liquid scintillator detector and the associated muon veto detect…
EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving
Shaoting Feng, Yuhan Liu, Hanchen Li +11
Reusing KV cache is essential for high efficiency of Large Language Model (LLM) inference systems. With more LLM users, the KV cache footprint can easily exceed GPU memory capacity…
A Low-energy Threshold and Multi-messenger Trigger System for the JUNO Experiment
Thomas Adam, Fengpeng An, Costas Andreopoulos +563
The paper presents a new multi‑messenger trigger system for the JUNO liquid‑scintillator detector that lowers the energy threshold to about 110 keV and adds real‑time monitoring of…
METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation
Siddhant Ray, Rui Pan, Zhuohan Gu +5
RAG (Retrieval Augmented Generation) allows LLMs (large language models) to generate better responses with external knowledge, but using more external knowledge often improves gene…
VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
Jiayi Yao, Samuel Shen, Kuntai Du +7
The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression methods, such as token droppin…
Initial performance results of the JUNO detector
Angel Abusleme, Thomas Adam, Kai Adamowicz +1131
The Jiangmen Underground Neutrino Observatory (JUNO) started physics data taking on 26 August 2025. JUNO consists of a 20-kton liquid scintillator central detector, surrounded by a…
AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving
Shaoting Feng, Hanchen Li, Kuntai Du +8
Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing L…
DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
Yuhan Liu, Yuyang Huang, Jiayi Yao +9
Compound AI systems, such as agentic systems, are an emerging trend in large-scale enterprise settings, with multiple LLMs specialized for different users, tasks, and/or roles work…
Prospects for geoneutrino detection with JUNO
Thomas Adam, Shakeel Ahmad, Rizwan Ahmed +625
Geoneutrinos, which are antineutrinos emitted during the decay of long-lived radioactive elements inside Earth, serve as a unique tool for studying the composition and heat budget…
LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
Yuhan Liu, Yihua Cheng, Jiayi Yao +8
KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV cach…
First measurement of reactor neutrino oscillations at JUNO
Angel Abusleme, Thomas Adam, Kai Adamowicz +1131
Neutrino oscillations, a quantum effect manifesting at macroscopic scales, are governed by lepton flavor mixing angles and neutrino mass-squared differences that are fundamental pa…