Metraipolis › archive › dc_132fe4880ae4

Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3 — arXiv:2609.28273

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28273
License (as archived)
CC0-1.0
Archived
2026-10-08T10:58:20.391Z
SHA-256 of the archived text
71359bae46a85e0571e8d1c198c463b9ad9f2b41d849c49b30987ed681697572
Stable URL of this page
https://metraipolis.com/documento/dc_132fe4880ae4

How to cite

Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3 — arXiv:2609.28273 — arXiv (en), https://arxiv.org/abs/2609.28273 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_132fe4880ae4 (Metraipolis archive dc_132fe4880ae4, sha256 71359bae46a85e0571e8d1c198c463b9ad9f2b41d849c49b30987ed681697572)
BibTeX
@misc{dc132fe4880ae4,
  title = {Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3 — arXiv:2609.28273},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28273},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_132fe4880ae4; sha256 71359bae46a85e0571e8d1c198c463b9ad9f2b41d849c49b30987ed681697572},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28273. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

State tracking from sequential observations can require both retaining information and updating it by composing observed operations. We extend Mamba-3's diagonal transition with an input-dependent low-rank reflection term to support noncommutative state tracking, in which the order of operations matters. The rank-one update couples state coordinates along an input-dependent direction, enabling non-diagonal state transitions within a single Mamba-3 block. The extension preserves Mamba-3's exponential-trapezoidal discretization, rotary embeddings (RoPE), and readout. For training, we adapt chunkwise computation to parallelize the proposed recurrence within each chunk. Experiments cover group word problems with discrete inputs and a shell game with continuous observations, in which a policy is trained by behavioral cloning. Among the models selected for their strong performance under fixed timing, the proposed model maintains higher tracking success on longer swap sequences in the shell game with continuous observations and timing jitter. These experiments show that the proposed method achieves high accuracy on the evaluated non-commutative tracking tasks, improving on standard Mamba-3. The extension thus offers a Mamba-3-based approach to non-commutative state tracking.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.28273 — 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 2026-10-08T10:06:16.843Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).