Tootfinder

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

Google is testing a new ad format in AI Mode that displays retailers selling the products a user is searching for in a Sponsored box (Vidhya Srinivasan/Google Ads & Commerce Blog)
https://blog.google/products/ads-commerce/agentic-commerce…

New tech and tools for retailers to succeed in an agentic shopping era
An overview of Google’s new open standard for agentic commerce and AI tools to help retailers connect with shoppers and drive sales.

The people who insist on waiting for some court's ruling before calling out and condemning a genocide are not just moving the goal post, deep down they must understand that by the time that court has come to a decision that displeases our ruling class, their representatives will have been silenced and their institution defamed to give the ideological basis to dismiss the court's ruling entirely.

Threats Against Routers
"The FBI, NSA, and co-sealing agencies encourage SOHO router users to change default usernames and passwords, disable remote management interfaces from the Internet, update to latest firmware versions, and upgrade end-of-support devices. Users should also carefully consider certificate warnings in web browsers and email clients."

So the MacBook Neo is both selling well and well reviewed. It has the same processor and RAM as in my iPhone.
What if Apple made a MacBook IPhone? iPhone shaped, iOS-running device that runs macOS once you plug into an external display and mouse/keyboard…