GeoGosha

Predicting Human Mobility Flows in Cities Using Deep Learning on Satellite Imagery. Nature Communications. https://www.nature.com/articles/s41467-025-65373-z

Researchers from TU Delft working on Graphs and Data https://graphsdataseminar-tudelft.github.io/#upcoming-talks Upcoming Talks [December 4th, 2025] Floor Plan Similarity as Graph Comparison Problem Speaker: Casper van Engelenburg Time: 15:45 - 16:05 Location: Electrical Engineering, Mathematics and Computer Sciences LB 01.170 Timmanzaal Zoom: link Abstract: When graphs encode spatial layouts, how can we compare them in a way that is both expressive and fast? Many methods for computing the similarity between two graphs rely on computationally expensive cross-graph message passing, which drastically limits the scalability of such methods. I will present an alternative viewpoint: learn graph representations independently and compute similarity only at the end using a differentiable graph kernel on the node embeddings. This preserves structural sensitivity while making comparison far more efficient, offering a practical route to scalable similarity learning of (spatial) graphs.

btw looks exactly like a map from Mirror's edge

In case you would ever need to defend your digital twin proposal via potential use case: Japan be like: https://jgtimes.org/articles/4_PLATEAU

Play: guess country in 60 sec: https://playabledatalab.github.io/006_GEOHANGMAN/

https://github.com/PlayableDataLab (https://playabledatalab.github.io/004_tourist-minesweeper/) это Сапёр если что :)

📰 Представили наши работы на ICOMP'25 Наша команда Sber AI Lab вернулась с конференции ICOMP'25 в Абу-Даби, где мы представили наши последние статьи и библиотеки Наши статьи: 🔘 3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark 🔘 LightAutoDS-Tab Open-Source библиотеки: 🔘 RIDE 🔘 Tsururu Поддержите наши решения звездочками на GitHub! ⭐ #новости ❤️ @sb_ai_lab

О как 👇🏽 а RIDE то наш слоняра! Ну как наш, общий, конечно, слоняра Собственно, папир: https://link.springer.com/content/pdf/10.1140/epjds/s13688-025-00542-0.pdf