Metraipolis › archive › dc_50f07585474f

Tensor Field Models — arXiv:2608.18808

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18808
License (as archived)
CC0-1.0
Archived
2026-10-18T13:53:26.675Z
SHA-256 of the archived text
cd8df9a3b72918dc81a638ff5b84c96b97216aab842d868bb907e5bbafe85216
Stable URL of this page
https://metraipolis.com/documento/dc_50f07585474f

How to cite

Tensor Field Models — arXiv:2608.18808 — arXiv (en), https://arxiv.org/abs/2608.18808 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50f07585474f (Metraipolis archive dc_50f07585474f, sha256 cd8df9a3b72918dc81a638ff5b84c96b97216aab842d868bb907e5bbafe85216)
BibTeX
@misc{dc50f07585474f,
  title = {Tensor Field Models — arXiv:2608.18808},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18808},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50f07585474f; sha256 cd8df9a3b72918dc81a638ff5b84c96b97216aab842d868bb907e5bbafe85216},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18808. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper introduces Tensor Field Models (TFMs), realization-level Mathematical Structures in which a learned Operator maps a product of admissible component-section families to a prescribed family of time-dependent tangent sections on a Generative State Manifold. Analytic and dynamical restrictions are encoded through the choice of admissible families rather than imposed by the root definition. Constructed, component-separable, and Tensor Bundle TFMs provide structured refinements of this common object. In the conditional realizations considered here, a structured condition $c=(c_1,\ldots,c_n)$ is mapped componentwise to a reusable collection $\mathbf H_c=(H_{c_1}^{(1)},\ldots,H_{c_n}^{(n)})$. In the architectures evaluated here, the component representations remain distinct and are combined only by the Field Operator to produce the generated Vector Field. All learned models are trained using Flow Matching. Experiments show that TFMs can improve performance and that amortized sampling enabled by reusable condition representations can accelerate generation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Differential Geometry (math.DG).
Pagina del lavoro: https://arxiv.org/abs/2608.18808 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T13:50:58.940Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).