中文
相关论文

相关论文: The Kerimov-Alekberli Model: An Information-Geomet…

200 篇论文

As large language models (LLMs) are increasingly deployed in high-stakes and operational settings, evaluation strategies based solely on aggregate accuracy are often insucient to characterize system reliability. This study proposes a…

人工智能 · 计算机科学 2026-05-06 Hikmat Karimov , Rahid Zahid Alekberli

This paper deals with the problem of identifying and estimating dynamical parameters of continuous-time quantum open systems, in the input-output formalism. First, we characterise the space of identifiable parameters for ergodic dynamics,…

量子物理 · 物理学 2019-01-04 Madalin Guta , Jukka Kiukas

We propose that unconstrained artificial intelligence obeys a Second Law analogous to thermodynamics, where ethical entropy, defined as a measure of divergence from intended goals, increases spontaneously without continuous alignment work.…

人工智能 · 计算机科学 2025-11-19 Samih Fadli

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

As autonomous systems grow more advanced, objective metrics to evaluate their ethical and legal compliance are critical for informing end users of their limitations and ensuring accountability of those who misuse them. Current ethical…

We propose an information-geometric signature of nonconservative driving that detects violations of detailed balance using the Kullback--Leibler divergence and the Fisher information. For Markov jump processes satisfying detailed balance,…

统计力学 · 物理学 2026-05-06 Andrea Auconi , Sosuke Ito

The rapid integration of AI algorithms in safety-critical applications such as autonomous driving and healthcare is raising significant concerns about the ability to meet stringent safety standards. Traditional tools for formal safety…

人工智能 · 计算机科学 2026-01-21 Oliver Schön , Zhengang Zhong , Sadegh Soudjani

AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing has improved the behavior of modern language models, but aligned behavior does not by…

人工智能 · 计算机科学 2026-05-27 Yige Li , Yunhao Feng , Jun Sun

Recent advancements have revealed new links between information geometry and classical stochastic thermodynamics, particularly through the Fisher information (FI) with respect to time. Recognizing the non-uniqueness of the quantum Fisher…

量子物理 · 物理学 2025-10-07 Laetitia P. Bettmann , John Goold

With the increasingly widespread adoption of AI in healthcare, maintaining the accuracy and reliability of AI models in clinical practice has become crucial. In this context, we introduce novel methods for monitoring the performance of…

人工智能 · 计算机科学 2023-11-27 Vasantha Kumar Venugopal , Abhishek Gupta , Rohit Takhar , Vidur Mahajan

Benchmarks are the primary tool for assessing progress in artificial intelligence (AI), yet current practice evaluates models on isolated test suites and provides little guidance for reasoning about generality or autonomous…

人工智能 · 计算机科学 2025-12-05 Przemyslaw Chojecki

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

人工智能 · 计算机科学 2025-05-12 Markov Grey , Charbel-Raphaël Segerie

Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core…

密码学与安全 · 计算机科学 2026-05-26 Dan Ristea , Vasilios Mavroudis

When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…

Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital intensity, physical bottlenecks, organizational inertia, and specialized supply chains. By…

人工智能 · 计算机科学 2026-05-05 Wesley Shu , Peng Wei

The training algorithms for AI systems all introduce far-from-equilibrium dynamical processes, and understanding the irreversibility of these algorithms is a fundamental step towards understanding the learning dynamics of modern AI systems.…

统计力学 · 物理学 2026-05-22 Liu Ziyin , Yuanjie Ren , Adam Levine , Isaac Chuang

This paper develops KL-Ergodic Exploration from Equilibrium ($\text{KL-E}^3$), a method for robotic systems to integrate stability into actively generating informative measurements through ergodic exploration. Ergodic exploration enables…

机器人学 · 计算机科学 2020-12-08 Ian Abraham , Ahalya Prabhakar , Todd D. Murphey

The consistency of AI-native applications depends on the behavioral consistency of the model endpoints that power them. Traditional reliability metrics such as uptime, latency and throughput do not capture behavioral change, and an endpoint…

人工智能 · 计算机科学 2026-03-20 Jonah Leshin , Manish Shah , Ian Timmis , Daniel Kang

As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…

密码学与安全 · 计算机科学 2025-05-13 Krti Tallam

Optimum designs for parameter estimation in generalized regression models are standardly based on the Fisher information matrix (cf. Atkinson et al (2014) for a recent exposition). The corresponding optimality criteria are related to the…

统计理论 · 数学 2015-07-28 Katarína Burclová , Andrej Pázman
‹ 上一页 1 2 3 10 下一页 ›