Metraipolis › archive › dc_fee2a09e16c4

TensorSSM: Memorizing Spatial Position in Dynamic State Space for Tensor Core Generation — arXiv:2610.40871

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40871
License (as archived)
CC0-1.0
Archived
2026-11-03T05:40:36.713Z
SHA-256 of the archived text
23060a4bc11a26eed06246b8d20b4de941922ef615378238d395af8803f716f8
Stable URL of this page
https://metraipolis.com/documento/dc_fee2a09e16c4

How to cite

TensorSSM: Memorizing Spatial Position in Dynamic State Space for Tensor Core Generation — arXiv:2610.40871 — arXiv (en), https://arxiv.org/abs/2610.40871 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fee2a09e16c4 (Metraipolis archive dc_fee2a09e16c4, sha256 23060a4bc11a26eed06246b8d20b4de941922ef615378238d395af8803f716f8)
BibTeX
@misc{dcfee2a09e16c4,
  title = {TensorSSM: Memorizing Spatial Position in Dynamic State Space for Tensor Core Generation — arXiv:2610.40871},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40871},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fee2a09e16c4; sha256 23060a4bc11a26eed06246b8d20b4de941922ef615378238d395af8803f716f8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40871. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-dimensional tensors are ubiquitous in real-world applications but lead to massive storage overhead. Functional tensor decomposition addresses this by employing neural networks to map element coordinates to tensor cores, significantly reducing the parameters for data compression. However, existing functional methods typically flatten high-order tensors into 1D sequences. This folding operation causes highly overlapping local coordinate sequences and struggles to capture complex cross-mode spatial dependencies, severely limiting their expressiveness on diverse datasets. To tackle these challenges, we propose TensorSSM, a novel Implicit Neural Representation (INR) for functional decomposition method that memorizes spatial positions within a dynamic State Space Model (SSM). Specifically, TensorSSM first decomposes mode-wise coordinates into sequences spit by K-ary rule, encoding spatial tokens from coarse to fine, which effectively captures spatial variations. Furthermore, we extend the SSM's state space to explicitly map cross-mode spatial dependencies, allowing inter-mode interactions to enhance the updates of each mode. By integrating cross-mode information from previous hidden states into the current state transitions, TensorSSM effectively expands tensor representation along two dimensions: the sequence dimension for coarse-to-fine spatial tokens, and the state dimension for cross-mode memorization. This design effectively integrates spatial information into the state space and the tensor core, substantially advancing the state adaptability and enhancing the expressiveness of the data compression. Extensive experiments demonstrate that TensorSSM achieves significantly high reconstruction accuracy and storage efficiency, exhibiting robust expressiveness across diverse tensor datasets without relying on strict spatial assumptions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.40871 — 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 2026-11-03T05:26:18.774Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).