Metraipolis › archive › dc_4fe249682c04

I-SplineFlow: Learning Monotone Spline Stochastic Interpolant Schedulers for Few-Step Generation — arXiv:2609.27963

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27963
License (as archived)
CC0-1.0
Archived
2026-10-08T10:57:29.352Z
SHA-256 of the archived text
7a8c125e3370cca4784913d0fa2b9590b018e17e781b92b7c9ec03daa3eaba79
Stable URL of this page
https://metraipolis.com/documento/dc_4fe249682c04

How to cite

I-SplineFlow: Learning Monotone Spline Stochastic Interpolant Schedulers for Few-Step Generation — arXiv:2609.27963 — arXiv (en), https://arxiv.org/abs/2609.27963 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fe249682c04 (Metraipolis archive dc_4fe249682c04, sha256 7a8c125e3370cca4784913d0fa2b9590b018e17e781b92b7c9ec03daa3eaba79)
BibTeX
@misc{dc4fe249682c04,
  title = {I-SplineFlow: Learning Monotone Spline Stochastic Interpolant Schedulers for Few-Step Generation — arXiv:2609.27963},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27963},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fe249682c04; sha256 7a8c125e3370cca4784913d0fa2b9590b018e17e781b92b7c9ec03daa3eaba79},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27963. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Few-step generation with pretrained diffusion and flow models can be accelerated by lightweight training that optimizes the sampling trajectory rather than the network. A recent approach parameterizes the stochastic interpolant (SI) scheduler as a smooth curve whose control points enforce the three properties an SI scheduler must satisfy: fixed boundary conditions, a monotone signal-to-noise ratio (SNR), and differentiability. Existing parameterizations use globally supported polynomial bases, where every control point moves the whole curve and higher expressiveness needs a higher degree, which couples distant regions of the schedule during optimization. We introduce \emph{I-SplineFlow}, which parameterizes the scheduler with integrated monotone splines (I-splines). I-splines decouple the polynomial degree from the number of mixture weights, so support width and smoothness can be chosen per model at a fixed weight count, and the compactly supported derivative basis makes the scheduler Jacobian orders of magnitude better conditioned than a Bézier basis. Boundary conditions and a strictly monotone SNR hold by construction, with no ordering constraint on the parameters and closed-form velocity derivatives. Across diffusion (EDM) and flow (ReFlow, Simple ReFlow) models, I-SplineFlow improves few-step FID over Bézier scheduling in most settings, most clearly at the lowest NFEs, and trains in minutes. Ablations show that both the degree freedom and the monotonicity constraint are needed. The code will be released upon acceptance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.27963 — 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 2026-10-08T10:06:16.762Z 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).