Tootfinder

🇺🇦 Auf radioeins läuft...
Yukimi, Little Dragon:
🎵 Get It Over
#NowPlaying #Yukimi #LittleDragon
https://open.spotify.com/track/5sJUrTiOlAdoKO8V81spAv

Great new catchy, brief, punchy EP by Brooklyn garage punks DR. DENCE. Almost has an Aussie pub rock feel, but like, yknow, in New York. It rips. Four great, fast, fuzzy songs.
https://doctoredtapes.bandcamp.com/album/sick-dumb-spam

Memo: WaPo won't send sports staffers to cover the Winter Olympics in Italy, as it assesses financial priorities for 2026, following reports of expected layoffs (Benjamin Lindsay/The Wrap)
https://www.thewrap.com/media-platforms/jo<…

Washington Post Cancels On-Site Winter Olympics Coverage Ahead of Expected Layoffs
Managing Editor Kimi Yoshino says the decision to not send reporters to the Games comes after assessing financial priorities.

UrbanFM: Scaling Urban Spatio-Temporal Foundation Models
Wei Chen, Yuqian Wu, Junle Chen, Xiaofang Zhou, Yuxuan Liang
https://arxiv.org/abs/2602.20677 https://arxiv.org/pdf/2602.20677 https://arxiv.org/html/2602.20677
arXiv:2602.20677v1 Announce Type: new
Abstract: Urban systems, as dynamic complex systems, continuously generate spatio-temporal data streams that encode the fundamental laws of human mobility and city evolution. While AI for Science has witnessed the transformative power of foundation models in disciplines like genomics and meteorology, urban computing remains fragmented due to "scenario-specific" models, which are overfitted to specific regions or tasks, hindering their generalizability. To bridge this gap and advance spatio-temporal foundation models for urban systems, we adopt scaling as the central perspective and systematically investigate two key questions: what to scale and how to scale. Grounded in first-principles analysis, we identify three critical dimensions: heterogeneity, correlation, and dynamics, aligning these principles with the fundamental scientific properties of urban spatio-temporal data. Specifically, to address heterogeneity through data scaling, we construct WorldST. This billion-scale corpus standardizes diverse physical signals, such as traffic flow and speed, from over 100 global cities into a unified data format. To enable computation scaling for modeling correlations, we introduce the MiniST unit, a novel split mechanism that discretizes continuous spatio-temporal fields into learnable computational units to unify representations of grid-based and sensor-based observations. Finally, addressing dynamics via architecture scaling, we propose UrbanFM, a minimalist self-attention architecture designed with limited inductive biases to autonomously learn dynamic spatio-temporal dependencies from massive data. Furthermore, we establish EvalST, the largest-scale urban spatio-temporal benchmark to date. Extensive experiments demonstrate that UrbanFM achieves remarkable zero-shot generalization across unseen cities and tasks, marking a pivotal first step toward large-scale urban spatio-temporal foundation models.
toXiv_bot_toot

#YouMustListenToNerveEveryday

【プランクスターズ】わちきの好きな「nerve」(BiS)を歌ってた【カン・ニャン生誕祭】 by YouKun 法明自由気まま自己満足CHANNEL
Listen now on your favorite streaming service. Powered by Songlink/Odesli, an on-demand, customizable smart link service to help you share songs, albums, podcasts and more.