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

We introduce $\textbf{SimuHome}$, a high-fidelity smart home simulator and a benchmark of 600 episodes for LLM-based smart home agents. Existing smart home benchmarks treat the home as a static system, neither simulating how device…

With the advancement of large language models (LLMs), solving complex reasoning tasks has gained increasing attention. Inference-time computation methods (e.g., Best-of-N, beam search, et al.) are particularly valuable as they can enhance…

Accurate and computationally-viable representations of clouds and turbulence are a long-standing challenge for climate model development. Traditional parameterizations that crudely but efficiently approximate these processes are a leading…

Due to embedded systems` stringent design constraints, much prior work focused on optimizing energy consumption and/or performance. Since embedded systems typically have fewer cooling options, rising temperature, and thus temperature…

This work explores the consistency of small LLMs (2B-8B parameters) in answering multiple times the same question. We present a study on known, open-source LLMs responding to 10 repetitions of questions from the multiple-choice benchmarks…

Cloud computing is essential for modern enterprises, requiring robust tools to monitor and manage Large-Scale Cloud Systems (LCS). Traditional monitoring tools often miss critical insights due to the complexity and volume of LCS telemetry…

The growing demand for on-device large language model (LLM) inference is driving interest in deploying lightweight, cost-effective AI solutions on edge hardware. Single-board computers (SBCs) such as the Raspberry Pi and Orange Pi offer a…

As Large Language Models (LLMs) are rapidly growing in popularity, LLM inference services must be able to serve requests from thousands of users while satisfying performance requirements. The performance of an LLM inference service is…

We consider blocks of quantum spins in a chain at thermal equilibrium, focusing on their properties from a thermodynamical perspective. Whereas in classical systems the temperature behaves as an intensive magnitude, a deviation from this…

Extended reasoning models represent a transformative shift in Large Language Model (LLM) capabilities by enabling explicit test-time computation for complex problem solving. However, the optimal configuration of sampling temperature and…

Deploying large language models on-device for always-on personal agents demands sustained inference from hardware tightly constrained in power, thermal envelope, and memory. We benchmark Qwen 2.5 1.5B (4-bit quantised) across four…

This study examines how Large Language Models (LLMs) perform when tackling quantitative management decision problems in a zero-shot setting. Drawing on 900 responses generated by five leading models across 20 diverse managerial scenarios,…

Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a percentage point. At the same time, the computational cost of evaluating modern LLMs has…

Though the existence of two-level systems (TLS) is widely accepted to explain low temperature anomalies in many physical observables, knowledge about their properties is very rare. For silica which is one of the prototype glass-forming…

When ML algorithms are deployed to automate human-related decisions, human agents may learn the underlying decision policies and adapt their behavior. Strategic Classification (SC) has emerged as a framework for studying this interaction…

Serverless computing is increasingly popular because of its lower cost and easier deployment. Several cloud service providers (CSPs) offer serverless computing on their public clouds, but it may bring the vendor lock-in risk. To avoid this…

Large language models (LLMs) have achieved remarkable results in wide range of domains. However, the accuracy and robustness of one-shot LLM predictions remain highly sensitive to the examples and the diversity among ensemble members. This…

Thermal errors in machine tools significantly impact machining precision and productivity. Traditional thermal error correction/compensation methods rely on measured temperature-deformation fields or on transfer functions. Most existing…

The proliferation of Large Language Models (LLMs) has been accompanied by a reliance on cloud-based, proprietary systems, raising significant concerns regarding data privacy, operational sovereignty, and escalating costs. This paper…

Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…