Metraipolis › archive › dc_cbfb66a4f9b2

Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow — arXiv:2609.25131

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25131
License (as archived)
CC0-1.0
Archived
2026-10-08T15:07:19.926Z
SHA-256 of the archived text
d5e970df38278f8097ad91271d13e639ee96acc74a1f985f1018b82d39af62bd
Stable URL of this page
https://metraipolis.com/documento/dc_cbfb66a4f9b2

How to cite

Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow — arXiv:2609.25131 — arXiv (en), https://arxiv.org/abs/2609.25131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbfb66a4f9b2 (Metraipolis archive dc_cbfb66a4f9b2, sha256 d5e970df38278f8097ad91271d13e639ee96acc74a1f985f1018b82d39af62bd)
BibTeX
@misc{dccbfb66a4f9b2,
  title = {Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow — arXiv:2609.25131},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25131},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbfb66a4f9b2; sha256 d5e970df38278f8097ad91271d13e639ee96acc74a1f985f1018b82d39af62bd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Uniform discrete flow permits repeated updates at every generation position. While continued revision supports correction of wrong tokens, it also exposes correct intermediate predictions to later errors. An experiment on Sudoku puzzles shows that 9.4% of generated cells are correct at an intermediate step but incorrect in the final output. We introduce generation order into uniform discrete flow through selective absorption, which fixes chosen predictions while preserving the uniform flow velocity at active positions. To prioritize reliable predictions for absorption, we propose Low-Entropy Discrete Flow (LEDFlow), a training-free sampler that adaptively orders absorption by local entropy. By decomposing absorption error into joint dependence and conditional prediction terms, we show that, under entropy-error regularity, selecting the lowest-entropy positions under a fixed absorption count minimizes an upper bound on the conditional term. We further analyze sensitivity of global lookahead, whose worst-case decision-error bound grows with lookahead window under an imperfect denoiser. Across reasoning benchmarks, LEDFlow attains 0.845 Nikoli Sudoku solve accuracy, with largest gains on strongly constrained tasks. On a text-to-image generation benchmark it attains the best overall score among decode-time samplers, and on multimodal understanding it improves over the default sampler on all six benchmarks, at an inference cost comparable to standard flow sampling.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.25131 — 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 2026-10-08T14:37:29.376Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).