Metraipolis › archive › dc_e64d4eeea0cf

Diffusion Language Models as Open Quantum Systems — arXiv:2610.21672

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.21672
License (as archived): CC0-1.0
Archived: 2026-10-16T10:02:17.749Z
SHA-256 of the archived text: d1420a7940849c967a776103b92f9a1cf111f0984472bfca546e0ab1531aa36e
Stable URL of this page: https://metraipolis.com/documento/dc_e64d4eeea0cf

How to cite

Diffusion Language Models as Open Quantum Systems — arXiv:2610.21672 — arXiv (en), https://arxiv.org/abs/2610.21672 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e64d4eeea0cf (Metraipolis archive dc_e64d4eeea0cf, sha256 d1420a7940849c967a776103b92f9a1cf111f0984472bfca546e0ab1531aa36e)

BibTeX

@misc{dce64d4eeea0cf,
  title = {Diffusion Language Models as Open Quantum Systems — arXiv:2610.21672},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21672},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e64d4eeea0cf; sha256 d1420a7940849c967a776103b92f9a1cf111f0984472bfca546e0ab1531aa36e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21672. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion language models generate text by reversing a classical diffusion process over token sequences. We show that their continuous-time forward and reverse dynamics can be embedded in the framework of open quantum systems, which describes quantum systems interacting with their environment. This connection provides a basis for extending diffusion sampling to superpositions of sentence states and for modifying the underlying generation dynamics. We construct a $\tau$-leaping unraveling scheme that simulates stochastic trajectories of these states while updating multiple token positions at each step. This enables generation conditioned on superposed prompts or thoughts, which we call Superposition of Prompts (SoP) and Superposition of Thoughts (SoT). The same formulation yields Quantum-Inspired Remasking (QIR): perturbing the masked-diffusion dynamics produces a confidence-based rule for revising previously generated tokens. Experiments with pretrained diffusion language models show that superposition-based generation can retain information from conditioning components not selected at the final measurement, while QIR improves LLM-assessed text quality when applied at an appropriate stage of generation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL); Quantum Physics (quant-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.21672 — 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 2026-10-16T08:44:47.761Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).