paper-with-me

Papers

Turbulence-like 5/3 spectral scaling in contextual representations of language as a complex system

2026-04-07 · Zhongxin Yang, Chun Bao, Yuanwei Bin, Xiang I. A. Yang, Shiyi Chen arxiv

Natural language is a complex system that exhibits robust statistical regularities. Here, we represent text as a trajectory in a high-dimensional embedding space generated by transformer-based language models, and quantify scale-dependent fluctuations along the token sequence using an embedding-step signal. Across multiple languages and corpora, the resulting power spectrum exhibits a robust power law with an exponent close to $5/3$ over an extended frequency range. This scaling is observed consistently in contextual embeddings from both human-written and AI-generated text, but is absent in static word embeddings and is disrupted by randomization of token order. These results show that the observed scaling reflects multiscale, context-dependent organization rather than lexical statistics alone. By analogy with the Kolmogorov spectrum in turbulence, our findings suggest that semantic information is integrated in a scale-free, self-similar manner across linguistic scales, and provide a quantitative, model-agnostic benchmark for studying complex structure in language representations.

📄 PDF Abstract BibTeX arXiv:2604.05536

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PSTNet: Physically-Structured Turbulence Network

2026-03-09 · Boris Kriuk, Fedor Kriuk arxiv

Reliable real-time estimation of atmospheric turbulence intensity remains an open challenge for aircraft operating across diverse altitude bands, particularly over oceanic, polar, and data-sparse regions that lack operat…

Mitigating Spectral Bias in Neural Operators via High-Frequency Scaling for Physical Systems

2025-03-17 · Siavash Khodakarami, Vivek Oommen, Aniruddha Bora, George Em Karniadakis

Neural operators have emerged as powerful surrogates for modeling complex physical problems. However, they suffer from spectral bias making them oblivious to high-frequency modes, which are present in multiscale physical…

Pixel-Resolved Long-Context Learning for Turbulence at Exascale: Resolving Small-scale Eddies Toward the Viscous Limit

2025-07-22 · Junqi Yin, Mijanur Palash, M. Paul Laiu, Muralikrishnan Gopalakrishnan Meena 외 arxiv

Turbulence plays a crucial role in multiphysics applications, including aerodynamics, fusion, and combustion. Accurately capturing turbulence's multiscale characteristics is essential for reliable predictions of multiphy…

Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias

2025-05-25 · Hao Wu, Yuan Gao, Ruiqi Shu, Zean Han 외

Accurately predicting the long-term evolution of turbulence is crucial for advancing scientific understanding and optimizing engineering applications. However, existing deep learning methods face significant bottlenecks …

SSIM

A Spectral Condition for Feature Learning

2023-10-26 · Greg Yang, James B. Simon, Jeremy Bernstein

The push to train ever larger neural networks has motivated the study of initialization and training at large network width. A key challenge is to scale training so that a network's internal representations evolve nontri…

All