Mais, le #rn c'est différent :
« Vous direz qu’il a travaillé » : écoutes accablantes au procès pour emploi fictif du maire d’Orange - Le Parisien
Weighted Stochastic Differential Equation to Implement Wasserstein-Fisher-Rao Gradient Flow
Herlock Rahimi
https://arxiv.org/abs/2512.17878 https://arxiv.org/pdf/2512.17878 https://arxiv.org/html/2512.17878
arXiv:2512.17878v1 Announce Type: new
Abstract: Score-based diffusion models currently constitute the state of the art in continuous generative modeling. These methods are typically formulated via overdamped or underdamped Ornstein--Uhlenbeck-type stochastic differential equations, in which sampling is driven by a combination of deterministic drift and Brownian diffusion, resulting in continuous particle trajectories in the ambient space. While such dynamics enjoy exponential convergence guarantees for strongly log-concave target distributions, it is well known that their mixing rates deteriorate exponentially in the presence of nonconvex or multimodal landscapes, such as double-well potentials. Since many practical generative modeling tasks involve highly non-log-concave target distributions, considerable recent effort has been devoted to developing sampling schemes that improve exploration beyond classical diffusion dynamics.
A promising line of work leverages tools from information geometry to augment diffusion-based samplers with controlled mass reweighting mechanisms. This perspective leads naturally to Wasserstein--Fisher--Rao (WFR) geometries, which couple transport in the sample space with vertical (reaction) dynamics on the space of probability measures. In this work, we formulate such reweighting mechanisms through the introduction of explicit correction terms and show how they can be implemented via weighted stochastic differential equations using the Feynman--Kac representation. Our study provides a preliminary but rigorous investigation of WFR-based sampling dynamics, and aims to clarify their geometric and operator-theoretic structure as a foundation for future theoretical and algorithmic developments.
toXiv_bot_toot
This is Europe’s secret weapon against Trump: it could burst his AI bubble | Johnny Ryan | The Guardian
https://www.theguardian.com/commentisfree/2025/dec/17/europe-donald-trump-ai-bubble-us-economy-eu
« Vous direz qu’il a travaillé » : écoutes accablantes au procès pour emploi fictif du maire d’Orange - Le Parisien
https://www.leparisien.fr/faits-divers/vous-direz-…
Protest, lawbreaking, or terrorism? ICE opponents face ‘extremist’ label. - CSMonitor.com https://www.csmonitor.com/USA/Politics/2026/0114/terrorism-ice-protests-trump-noem
René Lévesque… l’identitaire ?
https://www.lapresse.ca/dialogue/chroniques/2025-11-27/rene-levesque-l-identitaire.php
We cooked a new feature for Godot and iOS lovers. A plugin to Godot to deploy to Xogot on iOS or iPad:
Details:
https://blog.xogot.com/introducing-xogot-connect-remote-debugging-for-godot-on-iphone-and-ipad/
Noël: une fabuleuse occasion pour enfin faire connaissance avec la fast-déco, prendre conscience de ces impacts,
ou pester qu'elle ait été exclue du récent débat public sur la fast-fashion.
Le cynisme débonnaire de ces grandes enseignes (françaises comme étrangères) me révulse: extractivisme, pollution plastique, dégâts sociaux...
La fast-déco n'a rien Š envier Š sa copine toxique la fast-fashion.
Ouais, parlons-en de la fast-déco.
Parlons-en beaucoup.
@… Best bet is if you have access to Linux or macOS, run "zipinfo" and/or "file" on your $target.zip to find out what it actually is you are creating:
$ zipinfo $target.zip
$ file $target.zip
Alternatively libarchive, even the one on Windows, might be able to tell you. in cmd.exe run this and look at the very last …
Allez on lit et on fait tourner, on lit pour que l'algo du parisien et du monde mette les articles en une, ça pourrait ouvrir les yeux de certains de nos concitoyens. Article du monde offert.
« C’est Jean-Marie Le Pen qui décidait qui travaillait pour qui et voilŠ » : au procès du RN, la sidérante légèreté d’un ancien député européen - Le Parisien