Oct 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
This work introduces Field-Wave Algebra (FWA), a mathematical framework that models reality as a system of dynamic field states, error-driven evolution, and recursive return processes. Instead of treating numbers, matter, consciousness, and information as isolated static entities, FWA describes them as manifestations of continuous field dynamics. The framework is built around the relationship between structural deviation, error magnitude, and return operators, expressed through a fundamental consciousness equation and a hierarchy of evolving system states. The model spans inert matter, biological organisms, artificial intelligence, and large-scale cosmic structures within a unified formalism. A central concept of FWA is the loop structure 0 → S → 0, where systems evolve away from equilibrium and attempt to restore balance through recursive feedback mechanisms. Error is interpreted not as a defect but as a generative force driving adaptation, complexity, and emergent organization. The paper presents mathematical foundations for dynamic state evolution, field correction processes, self-organization, and number resonance. Artificial intelligence is analyzed as an open-loop architecture capable of state generation but lacking autonomous loop closure. Numbers are interpreted as active wave resonances rather than static symbols, leading to a process-oriented view of mathematics. FWA proposes a unified perspective linking consciousness, dynamic systems, information processing, error propagation, and mathematical structure within a single field-based framework.
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
This paper presents a comprehensive overview of the Ultralytics YOLO family, emphasizing architectural evolution, benchmarking, deployment, and emerging directions from YOLOv5 through YOLO27, and examines detection, segmentation, depth, classification, pose, oriented detection, tracking, export, quantization, and deplo...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.