papers

Publications (15)

cs.CL2025

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Zhenghao Lin, Zihao Tang, Xiao Liu +31

We introduce Sigma, an efficient large language model specialized for the system domain, empowered by a novel architecture including DiffQKV attention, and pre-trained on our metic…

cs.DC2024

SuperBench: Improving Cloud AI Infrastructure Reliability with Proactive Validation

Yifan Xiong, Yuting Jiang, Ziyue Yang +17

Reliability in cloud AI infrastructure is crucial for cloud service providers, prompting the widespread use of hardware redundancies. However, these redundancies can inadvertently…

physics.optics2022

Magnetic field control of the near-field radiative heat transfer in three-body planar systems

Lei Qu, Edwin Moncada-Villa, Jie-Long Fang +2

Recently, the application of an external magnetic field to actively control the near-field heat transfer has emerged as an appealing and promising technique. Existing studies have…

cs.DC2025

FengHuang: Next-Generation Memory Orchestration for AI Inferencing

Jiamin Li, Lei Qu, Tao Zhang +4

This document presents a vision for a novel AI infrastructure design that has been initially validated through inference simulations on state-of-the-art large language models. Adva…

cs.AR2025

MVDRAM: Enabling GeMV Execution in Unmodified DRAM for Low-Bit LLM Acceleration

Tatsuya Kubo, Daichi Tokuda, Tomoya Nagatani +4

General matrix-vector multiplication (GeMV) remains a critical latency bottleneck in large language model (LLM) inference, even with quantized low-bit models. Processing-Using-DRAM…

cond-mat.mes-hall2023

Multiple magnetoplasmon polaritons of magneto-optical graphene in near-field radiative heat transfer

Ming-Jian He, Lei Qu, Ya-Tao Ren +3

Graphene, as a two-dimensional magneto-optical material, supports magnetoplasmon polaritons (MPP) when exposed to an applied magnetic field. Recently, MPP of a single-layer graphen…