中文
相关论文

相关论文: Temperature in SLMs: Impact on Incident Categoriza…

200 篇论文

This study evaluates the efficiency of code generation by Large Language Models (LLMs) and measures their performance against human-crafted solutions using a dataset from Leetcode. We compare 18 LLMs, considering factors such as model…

软件工程 · 计算机科学 2024-08-01 Tristan Coignion , Clément Quinton , Romain Rouvoy

Current safety evaluations of large language models rely on single-shot testing, implicitly assuming that model responses are deterministic and representative of the model's safety alignment. We challenge this assumption by investigating…

机器学习 · 计算机科学 2025-12-17 Erik Larsen

Large language model (LLM) serving is becoming an increasingly important workload for cloud providers. Based on performance SLO requirements, LLM inference requests can be divided into (a) interactive requests that have tight SLOs in the…

分布式、并行与集群计算 · 计算机科学 2025-01-15 Archit Patke , Dhemath Reddy , Saurabh Jha , Chandra Narayanaswami , Zbigniew Kalbarczyk , Ravishankar Iyer

The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly influence how inputs are processed. These components differ…

密码学与安全 · 计算机科学 2026-05-29 Anna Wimbauer , Jonas Möller , Erik Imgrund , Konrad Rieck

Simulated annealing is an effective and general means of optimization. It is in fact inspired by metallurgy, where the temperature of a material determines its behavior in thermodynamics. Likewise, in simulated annealing, the actions that…

机器学习 · 计算机科学 2020-07-01 Avrim Blum , Chen Dan , Saeed Seddighin

In this work, ML models were used to predict the plasma temperature using the dataset obtained by implementing the CR-model for Na-like Krypton. The models included in the study are: Linear Regression, Lasso Regression, Support Vector…

等离子体物理 · 物理学 2025-05-05 Ashwini Malviya

The paper presents a sensitivity analysis of the factors affecting the optimal partitioning of a district heating network for distributed control. Leveraging a physics-based, distributed model predictive control framework and a…

系统与控制 · 电气工程与系统科学 2026-05-13 Audrey Blizard , Stephanie Stockar

Broadband seismometers are widely used in global observation networks deployed for geophysics research. Recently, the calibration of their sensitivity has become an important factor for ensuring observation accuracy. One of the limiting…

地球物理 · 物理学 2026-03-03 Tomofumi Shimoda , Wataru Kokuyama , Hideaki Nozato

Scale is often attributed as one of the factors that cause an increase in the performance of LLMs, resulting in models with billion and trillion parameters. One of the limitations of such large models is the high computational requirements…

机器学习 · 计算机科学 2024-05-09 Sher Badshah , Hassan Sajjad

Deploying Large Language Models (LLMs) on edge devices enhances privacy but faces performance hurdles due to limited resources. We introduce a systematic methodology to evaluate on-device LLMs, balancing capability, efficiency, and resource…

With the success of machine learning (ML) applied to climate reaching further every day, emulators have begun to show promise not only for weather but for multi-year time scales in the atmosphere. Similar work for the ocean remains nascent,…

User experience is a critical factor Large Language Model (LLM) serving systems must consider, where service level objectives (SLOs) considering the experience of individual requests and system level metrics (SLMs) considering the overall…

机器学习 · 计算机科学 2025-10-30 Zhibin Wang , Shipeng Li , Yuhang Zhou , Xue Li , Zhonghui Zhang , Nguyen Cam-Tu , Rong Gu , Chen Tian , Guihai Chen , Sheng Zhong

Modern deployments of Large Language Models (LLMs) increasingly require serving multiple models with diverse architectures, sizes, and specialization on shared, heterogeneous hardware. This setting introduces new challenges for resource…

人工智能 · 计算机科学 2026-05-20 Mert Yildiz , Pietro Spadaccino , Alexey Rolich , Francesca Cuomo , Andrea Baiocchi

Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy concerns or impractical due to network connection. Recent…

The evaluation of open-ended responses in serious games presents a unique challenge, as correctness is often subjective. Large Language Models (LLMs) are increasingly being explored as evaluators in such contexts, yet their accuracy and…

计算与语言 · 计算机科学 2025-04-18 Andrés Isaza-Giraldo , Paulo Bala , Lucas Pereira

Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs). We examined self-consistency (intra-model majority voting) and reasoning effort for…

计算机与社会 · 计算机科学 2026-05-01 Scott Frohn

Two-stage object detectors exhibit high accuracy and precise localization, especially for identifying small objects that are favorable for various edge applications. However, the high computation costs associated with two-stage detection…

计算机视觉与模式识别 · 计算机科学 2024-10-16 Yifan Gong , Yushu Wu , Zheng Zhan , Pu Zhao , Liangkai Liu , Chao Wu , Xulong Tang , Yanzhi Wang

Accurate on-chip temperature sensing is critical for the optimal performance of modern CMOS integrated circuits (ICs), to understand and monitor localized heating around the chip during operation. The development of quantum computers has…

As Large Language Models (LLMs) rise in popularity, it is necessary to assess their capability in critically relevant domains. We present a comprehensive evaluation framework, grounded in science communication research, to assess LLM…

Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…

机器学习 · 计算机科学 2025-10-08 Hanbo Huang , Yihan Li , Bowen Jiang , Bo Jiang , Lin Liu , Ruoyu Sun , Zhuotao Liu , Shiyu Liang