arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.10092cs.LGcs.AI
收藏

生成模型中数据生成的新方法

A novel approach to data generation in generative model

Korea University(高丽大学);Seoul National University(首尔大学)

JaeHong Kim, Jaewon Shim

AI总结:

本文提出 Convergent Fusion Paradigm (CFP) 理论,通过维度扩展与质变重新定义数据生成,解决 VAEs 和 LLMs 中的可识别性与幻觉问题,为高维学习动力学提供理论基础。

摘要:

变分自编码器(VAEs)及其他生成模型在人工智能中被广泛用于合成新数据。然而,当前方法依赖于欧几里得几何假设和统计近似,未能捕捉数据生成的结构化与涌现本质。本文提出 Convergent Fusion Paradigm (CFP) 理论,这是一种新型几何框架,通过整合伴随质变的维度扩展来重新定义数据生成。通过修改潜在空间几何以与涌现的高维结构交互,CFP 理论解决了可识别性问题以及大型语言模型(LLMs)中幻觉等意外伪影等关键挑战。CFP 理论基于两个关键概念假设,重新定义了生成模型如何构建数据与算法之间的关系。通过 CFP 理论的视角,我们批判性地审视了现有的度量学习方法。CFP 理论通过引入时间反转度量嵌入和结构收敛机制推进了这一视角,形成了一种新型几何方法,更好地将数据生成解释为结构化认知过程。除了计算层面的意义外,CFP 理论还为数据生成的本体论基础提供了哲学洞见。通过为高维学习动力学提供系统框架,CFP 理论为理解 AI 中的数据关系结构奠定了理论基础。最后,CFP 理论的未来研究将聚焦于其对完全实现质变的意义,并引入 Hilbert 空间在生成建模中的潜力。

英文摘要:

Variational Autoencoders (VAEs) and other generative models are widely employed in artificial intelligence to synthesize new data. However, current approaches rely on Euclidean geometric assumptions and statistical approximations that fail to capture the structured and emergent nature of data generation. This paper introduces the Convergent Fusion Paradigm (CFP) theory, a novel geometric framework that redefines data generation by integrating dimensional expansion accompanied by qualitative transformation. By modifying the latent space geometry to interact with emergent high-dimensional structures, CFP theory addresses key challenges such as identifiability issues and unintended artifacts like hallucinations in Large Language Models (LLMs). CFP theory is based on two key conceptual hypotheses that redefine how generative models structure relationships between data and algorithms. Through the lens of CFP theory, we critically examine existing metric-learning approaches. CFP theory advances this perspective by introducing time-reversed metric embeddings and structural convergence mechanisms, leading to a novel geometric approach that better accounts for data generation as a structured epistemic process. Beyond its computational implications, CFP theory provides philosophical insights into the ontological underpinnings of data generation. By offering a systematic framework for high-dimensional learning dynamics, CFP theory contributes to establishing a theoretical foundation for understanding the data-relationship structures in AI. Finally, future research in CFP theory will be led to its implications for fully realizing qualitative transformations, introducing the potential of Hilbert space in generative modeling.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑