用物理场模型替代传统语言模型，实现更连贯的文本生成。
Spectral Generative Flow Models: A Physics-Inspired Replacement for Vectorized Large Language Models
- 将文本生成视为连续场的演化过程，基于小波基与随机流体动力学。
- 通过谱域表示实现稀疏性与多尺度计算效率，避免全局注意力。
- 适合追求长程一致性与物理结构先验的生成模型研究者。
我们提出谱生成流模型（SGFMs），一种受物理启发的Transformer大语言模型替代方案。不同于将文本或视频表示为由注意力机制处理的离散标记序列，SGFMs将生成建模为在多尺度小波基下受约束随机动力学支配的连续场演化。该框架以局部算子、谱投影和类似纳维-斯托克斯的传输取代全局注意力，构建了基于连续性、几何与物理结构的生成机制。其核心创新包括：(i) 将文本与视频统一为随机偏微分方程轨迹的场论本体；(ii) 在小波域表示中实现稀疏性、尺度分离与计算效率；(iii) 通过受约束随机流确保稳定性、连贯性与不确定性传播。三者共同构成一种从根本上区别于自回归与扩散方法的生成架构，为下一代生成模型提供长程连贯性、多模态泛化与物理结构先验的原理性路径。
原文摘要 · Abstract (English)
We introduce Spectral Generative Flow Models (SGFMs), a physics-inspired alternative to transformer-based large language models. Instead of representing text or video as sequences of discrete tokens processed by attention, SGFMs treat generation as the evolution of a continuous field governed by constrained stochastic dynamics in a multiscale wavelet basis. This formulation replaces global attention with local operators, spectral projections, and Navier--Stokes-like transport, yielding a generative mechanism grounded in continuity, geometry, and physical structure. Our framework provides three key innovations: (i) a field-theoretic ontology in which text and video are unified as trajectories of a stochastic partial differential equation; (ii) a wavelet-domain representation that induces sparsity, scale separation, and computational efficiency; and (iii) a constrained stochastic flow that enforces stability, coherence, and uncertainty propagation. Together, these components define a generative architecture that departs fundamentally from autoregressive modeling and diffusion-based approaches. SGFMs offer a principled path toward long-range coherence, multimodal generality, and physically structured inductive bias in next-generation generative models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。