Skip to content

Commit 6680811

Browse files
pancettapancetta
committed
deploy: 5eba7ab 
1 parent 935a897 commit 6680811

File tree

2 files changed

+105
-10
lines changed

2 files changed

+105
-10
lines changed

‎references/index.html‎

Lines changed: 95 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3954,6 +3954,101 @@ <h2 id="year2025" class="year">2025 <span class="count-stat"></span></h2>
39543954
</div>
39553955

39563956

3957+
</div>
3958+
</li>
3959+
<li><div class="bibtex-entry-container">
3960+
<div>
3961+
<div class="col-md-3 col-sm-12 bibtex-ref-meta hidden">
3962+
<div class="row">
3963+
<div class="col-md-12 ref-label label label-default">
3964+
RadlerEtAl2025
3965+
</div>
3966+
</div>
3967+
</div>
3968+
3969+
<div class="bibtex-ref-entry">
3970+
<span id="RadlerEtAl2025">A. Radler, V. Seyfried, S. Pirker, J. Brandstetter, and T. Lichtenegger, “PAINT: Parallel-in-time Neural Twins for Dynamical System Reconstruction,” arXiv:2510.16004v1 [cs.AI], 2025 [Online]. Available at: <a href="http://arxiv.org/abs/2510.16004v1" target="_blank">http://arxiv.org/abs/2510.16004v1</a></span>
3971+
</div>
3972+
3973+
3974+
<div class="row mt-4">
3975+
<div class="btn-group btn-group-xs btn-group-justified" role="group">
3976+
<div class="btn-group btn-group-xs" role="group">
3977+
3978+
<button class="button" data-toggle="modal" data-target="#modalRadlerEtAl2025Bibtex" aria-expanded="false"
3979+
aria-controls="modalRadlerEtAl2025Bibtex">
3980+
BibTeX
3981+
</button>
3982+
3983+
</div>
3984+
<div class="btn-group btn-group-xs" role="group">
3985+
3986+
<button class="button" data-toggle="modal" data-target="#modalRadlerEtAl2025Abstract" aria-expanded="false"
3987+
aria-controls="modalRadlerEtAl2025Abstract">
3988+
Abstract
3989+
</button>
3990+
3991+
</div>
3992+
</div>
3993+
</div>
3994+
</div>
3995+
3996+
<div class="modal" id="modalRadlerEtAl2025Bibtex" tabindex="-1" role="dialog"
3997+
aria-labelledby="modalRadlerEtAl2025BibtexTitle" aria-hidden="true">
3998+
<div class="modal-background">
3999+
<div class="modal-card">
4000+
<div class="modal-content">
4001+
<header class="modal-card-head">
4002+
<div class="modal-card-head-content">
4003+
<div>
4004+
<p class="modal-card-title" id="modalRadlerEtAl2025BibtexTitle">
4005+
BibTeX entry <code>RadlerEtAl2025</code>
4006+
</p>
4007+
</div>
4008+
<button type="button" class="delete" data-dismiss="modal" aria-label="Close"><span
4009+
aria-hidden="true">&times;</span></button>
4010+
</div>
4011+
</header>
4012+
<section class="modal-card-body">
4013+
<pre class="abstract">@unpublished{RadlerEtAl2025,
4014+
author = {Radler, Andreas and Seyfried, Vincent and Pirker, Stefan and Brandstetter, Johannes and Lichtenegger, Thomas},
4015+
howpublished = {arXiv:2510.16004v1 [cs.AI]},
4016+
title = {PAINT: Parallel-in-time Neural Twins for Dynamical System Reconstruction},
4017+
url = {http://arxiv.org/abs/2510.16004v1},
4018+
year = {2025}
4019+
}
4020+
</pre>
4021+
</section>
4022+
</div>
4023+
</div>
4024+
</div>
4025+
</div>
4026+
4027+
4028+
<div class="modal" id="modalRadlerEtAl2025Abstract" tabindex="-1" role="dialog"
4029+
aria-labelledby="modalRadlerEtAl2025AbstractTitle" aria-hidden="true">
4030+
<div class="modal-background">
4031+
<div class="modal-card">
4032+
<div class="modal-content">
4033+
<header class="modal-card-head">
4034+
<div class="modal-card-head-content">
4035+
<div>
4036+
<p class="modal-card-title" id="modalRadlerEtAl2025AbstractTitle">
4037+
Abstract for BibTeX entry <code>RadlerEtAl2025</code>
4038+
</p>
4039+
</div>
4040+
<button type="button" class="delete" data-dismiss="modal" aria-label="Close"><span
4041+
aria-hidden="true">&times;</span></button>
4042+
</div>
4043+
</header>
4044+
<section class="modal-card-body">
4045+
Neural surrogates have shown great potential in simulating dynamical systems, while offering real-time capabilities. We envision Neural Twins as a progression of neural surrogates, aiming to create digital replicas of real systems. A neural twin consumes measurements at test time to update its state, thereby enabling context-specific decision-making. A critical property of neural twins is their ability to remain on-trajectory, i.e., to stay close to the true system state over time. We introduce Parallel-in-time Neural Twins (PAINT), an architecture-agnostic family of methods for modeling dynamical systems from measurements. PAINT trains a generative neural network to model the distribution of states parallel over time. At test time, states are predicted from measurements in a sliding window fashion. Our theoretical analysis shows that PAINT is on-trajectory, whereas autoregressive models generally are not. Empirically, we evaluate our method on a challenging two-dimensional turbulent fluid dynamics problem. The results demonstrate that PAINT stays on-trajectory and predicts system states from sparse measurements with high fidelity. These findings underscore PAINT’s potential for developing neural twins that stay on-trajectory, enabling more accurate state estimation and decision-making.
4046+
</section>
4047+
</div>
4048+
</div>
4049+
</div>
4050+
</div>
4051+
39574052
</div>
39584053
</li>
39594054
<li><div class="bibtex-entry-container">

‎sitemap.xml‎

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -366,36 +366,36 @@
366366
<loc>http://parallel-in-time.org/about/imprint.html</loc>
367367
</url>
368368
<url>
369-
<loc>http://parallel-in-time.org/codes/</loc>
370-
</url>
371-
<url>
372369
<loc>http://parallel-in-time.org/references/</loc>
373370
</url>
374371
<url>
375-
<loc>http://parallel-in-time.org/projects/</loc>
372+
<loc>http://parallel-in-time.org/events/upcoming/</loc>
376373
</url>
377374
<url>
378-
<loc>http://parallel-in-time.org/groups/</loc>
375+
<loc>http://parallel-in-time.org/events/past/</loc>
379376
</url>
380377
<url>
381-
<loc>http://parallel-in-time.org/methods/</loc>
378+
<loc>http://parallel-in-time.org/events/</loc>
382379
</url>
383380
<url>
384-
<loc>http://parallel-in-time.org/events/upcoming/</loc>
381+
<loc>http://parallel-in-time.org/projects/</loc>
385382
</url>
386383
<url>
387-
<loc>http://parallel-in-time.org/events/past/</loc>
384+
<loc>http://parallel-in-time.org/groups/</loc>
388385
</url>
389386
<url>
390-
<loc>http://parallel-in-time.org/events/</loc>
387+
<loc>http://parallel-in-time.org/methods/</loc>
391388
</url>
392389
<url>
393-
<loc>http://parallel-in-time.org/about/</loc>
390+
<loc>http://parallel-in-time.org/codes/</loc>
394391
</url>
395392
<url>
396393
<loc>http://parallel-in-time.org/news/</loc>
397394
</url>
398395
<url>
396+
<loc>http://parallel-in-time.org/about/</loc>
397+
</url>
398+
<url>
399399
<loc>http://parallel-in-time.org/</loc>
400400
</url>
401401
<url>

0 commit comments

Comments
 (0)