Dec 2026· Scientif Bulletin of Naval Academy· 0 citations
Abstract
Modeling and simulation (M&S) techniques have evolved from optional engineering
tools to indispensable pillars of modern maritime practice. This article presents a
comprehensive systematic review of the most important modeling and simulation
methodologies applied to maritime industry processes, including workflows for ship design,
shipyard fabrication and construction, port and terminal operations, vessel traffic management,
maintenance scheduling, supply chain logistics, and risk management procedures. The study
demonstrates that M&S techniques enable safer, more efficient, and more environmentally
sustainable operations, validated by scientific standards.
The COVID-19 pandemic served as a critical catalyst, consolidating the strategic value of
M&S as a central component of maritime resilience and innovation. This research traces the
evolution of M&S adoption from 2010 to 2025, identifying four dominant research directions:
maritime simulators, computational fluid dynamics (CFD)/finite element analysis (FEA),
digital twins, and artificial intelligence-based methods. The analysis reveals that while
traditional approaches dominated the 2010-2020 period, emerging technologies—particularly
digital twins and AI-based methods—have accelerated exponentially since 2020, reflecting the
maritime industry's accelerated digitalization. Forward projections through 2035 indicate that
AI-based methodologies will experience the highest growth rate at approximately 329%,
followed by digital twins at 147%, underscoring the fundamental transformation of maritime
research and practice. The integration of these advanced modeling approaches offers optimal
equilibrium between physical precision and computational efficiency for addressing complex
maritime challenges.
This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.
F. Xia, Amir Zamir, Zhi-Yang He et al.· 2018 IEEE/CVF Conference on...· 1,069 citations· ⚡112
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.
This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...
Masoud Mohseni, Artur Scherer, K. Johnson et al.· arXiv.org· 121 citations· ⚡9