2024-11-11
|
|
|
AI's "human in the loop" isn't
AI's ability to make – or assist with – important decisions is fraught: on the one hand, AI can often classify things very well, at a speed and scale that outstrips the ability of any reasonably resourced group of humans. On the other hand, AI is sometimes very wrong, in ways that can be terribly harmful.
Cory Doctorow
2024-09-30
|
|
|
Wahlbezirke Editor
Digitales Tool zum teilautomatisierten Zuschneiden neuer Wahlbezirke auf Grundlage von Bevölkerungsveränderungen.
2024-12-06
|
|
|
Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG
Ultra High Resolution (UHR) remote sensing imagery (RSI) (e.g. 100,000 × 100,000 pixels or more) poses a significant challenge for current Remote Sensing Multimodal Large Language Models (RSMLLMs). If choose to resize the UHR image to standard input image size, the extensive spatial and contextual information that UHR images contain will be neglected. Otherwise, the original size of these images often exceeds the token limits of standard RSMLLMs, making it difficult to process the entire image and capture long-range dependencies to answer the query based on the abundant visual context.
In this paper, we introduce ImageRAG for RS, a training-free framework to address the complexities of analyzing UHR remote sensing imagery. By transforming UHR remote sensing image analysis task to image’s long context selection task, we design an innovative image contextual retrieval mechanism based on the Retrieval-Augmented Generation (RAG) technique, denoted as ImageRAG. ImageRAG’s core innovation lies in its ability to selectively retrieve and focus on the most relevant portions of the UHR image as visual contexts that pertain to a given query. Fast path and slow path are proposed in this framework to handle this task efficiently and effectively. ImageRAG allows RSMLLMs to manage extensive context and spatial information from UHR RSI, ensuring the analysis is both accurate and efficient.
Zilun Zhang, Haozhan Shen, Tiancheng Zhao, Yuhao Wang, Bin Chen, Yuxiang Cai, Yongheng Shang, Jianwei Yin
2024-10-01
|
|
|
Mainzer Stadtwerke – Nachhaltigkeitsdashboard
2024-12-06
|
|
|
The Spatial Edge (Newsletter)
Helping you become a better geospatial data scientist in less than 5 minutes a week. Click to read The Spatial Edge, by Yohan, a Substack publication with thousands of subscribers.
2024-11-07
|
|
|
Samgeo
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
2024-10-08
|
|
|
D2045 Neue Horizonte - D2030
Gemeinsam mit 50 führenden Zukunftsforschenden sowie zwei Online-Dialogen wurden sieben Zukunftsbilder für ein klimaneutrales und sozial gerechtes Deutschland entwickelt. In der Studie „Neue Horizonte 2045 – Missionen für Deutschland“ werden diese Szenarien sowie daraus abgeleitete Handlungsempfehlungen für die Politik vorgestellt.
2024-12-07
|
|
|
The 15-Minute City
Let AI analyze any location worldwide based on the 15-minute city concept, where essentials like shopping, education, healthcare, transport, and leisure are within a 15-minute walk.
2024-11-07
|
|
|
Humanitarian OSM
2025-01-13
|
|
|
United for Smart Sustainable Cities (U4SSC) – United for Smart Sustainable Cities (U4SSC)
The United for Smart Sustainable Cities (U4SSC) initiative is a global UN collaboration, coordinated by ITU, UNEP and UNECE, and supported by a network of key partners, including UN-Habitat, CBD, ECLAC, FAO, UNDESA, UNDP, UNECA, UNESCO, UNEP, UNEP-FI, UNFCCC, UNIDO, UNOPS, UNU-EGOV, UN-Women, UNWTO, and WMO.
U4SSC serves as an international platform for exchanging knowledge and fostering partnerships to empower cities and communities in achieving the UN Sustainable Development Goals.
2024-12-21
|
|
|
Map of walkable neighborhoods
2024-11-07
|
|
|
Rapid 2.0: Verbesserte Geschwindigkeit und Effizienz in der Kartenbearbeitung
Wir launchen heute den neuen Rapid-Editor für OpenStreetMap (OSM)! Rapid 2.0 baut auf den Stärken der Vorgängerversion auf. Es ist nach wie vor ein leistungsfähiges und effizientes Kartenbearbeitungstool, das jedoch noch mehr Kartendetails, bessere Qualität und höhere Genauigkeit bietet.
2024-10-07
|
|
|
Roblox is launching a generative AI that builds 3D environments in a snap
2025-01-15
|
|
|
Index — The Philosophical Glossary of AI
2024-10-07
|
|
|
Maputnik
Maputnik is an open source visual editor for the MapLibre Style Specification .
2024-12-17
|
|
|
Maps Mania: Do You Live in 15 Minute City?
2024-11-16
|
|
|
Nationale Stadtentwicklungspolitik - Homepage - Themendossier "Hitze in der Stadt"
2025-01-07
|
|
|
How AI Really Learns: The Journey from Random Noise to Intelligence
A Story of How Machines Learn to Think Through Language
2024-10-21
|
|
|
KI-generierte Bilder: Schöne neue Welt der lächelnden Mittelschichtsjugend
2024-11-17
|
|
|
Smarte Bürgerbeteiligung mitgestalten
2024-11-26
|
|
|
Crafting Futures – Eine neue Vision für nachhaltige Städte
2024-12-29
|
|
|
Maps Mania: The AI Map Benchmark Test
2025-01-11
|
|
|
Google Launches Android XR, Its New AI-Powered Extended Reality Platform
2024-10-15
|
|
|
GitHub - NirDiamant/RAG_Techniques
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
2024-11-17
|
|
|
smarticipate – Opening up the smart city
2024-11-26
|
|
|
Maps Mania: Free Map Data Grabbers
2025-01-06
|
|
|
Projekt AUFGEHTS
Automatisiertes Verfahren zur Erstellung und Kalibrierung von Verkehrssimulationen auf Basis von Floating-Car-Daten
2024-11-28
|
|
|
Stuttgart Research Initiative „Discursive Transformation of Energy Systems“
Erforscht wird, wie mithilfe von Virtual und Augmented Reality ein Transformationsprozess mit den verschiedenen Stakeholdern in der Energieversorgung gestaltet werden kann. Dazu wird u. a. ein digitaler Zwilling urbaner Bestandsquartiere entwickelt.
2025-01-06
|
|
|
Fairness and Abstraction in Sociotechnical Systems
A key goal of the fair-ML community is to develop machine-learning based systems that, once introduced into a social context, can achieve social and legal outcomes such as fairness, justice, and due process. Bedrock concepts in computer science - such as abstraction and modular design - are used to define notions of fairness and discrimination, to produce fairness-aware learning algorithms, and to intervene at different stages of a decision-making pipeline to produce "fair" outcomes. In this paper, however, we contend that these concepts render technical interventions ineffective, inaccurate, and sometimes dangerously misguided when they enter the societal context that surrounds decision-making systems. We outline this mismatch with five "traps" that fair-ML work can fall into even as it attempts to be more context-aware in comparison to traditional data science. We draw on studies of sociotechnical systems in Science and Technology Studies to explain why such traps occur and how to avoid them. Finally, we suggest ways in which technical designers can mitigate the traps through a refocusing of design in terms of process rather than solutions, and by drawing abstraction boundaries to include social actors rather than purely technical ones.
Andrew D. Selbst, Danah Boyd, Sorelle A. Friedler, Suresh Venkatasubramanian, Janet Vertesi
2024-10-15
|
|
|
GeoJSON.io
GeoJSON.io ist ein interaktiver GeoJSON-Editor in Form einer Webanwendung.
2024-11-17
|
|
|
AI Logo Maker for Unique, Fast Designs
2024-10-23
|
|
|
Einsteiger-Leitfaden für ComfyUI: Meistern Sie Funktionen mit kostenlosem Online-Training
2024-11-25
|
|
|
Moderne Verwaltung ist transparent
2024-11-28
|
|
|
GitHub - ouseful-testing/robo-editor: A live editor for RosaeNLG PUG templates.
A live editor for RosaeNLG PUG templates. Contribute to ouseful-testing/robo-editor development by creating an account on GitHub.
2025-01-12
|
|
|
Neues 3D-Modell von Stability AI soll schnell genug für Echtzeit-Generierung sein
2024-10-24
|
|
|
Smart Cities Normen und Standards
Nationale und internationale Normen und Standards zum Thema Smart Cities können Sie hier nachlesen.
2024-11-25
|
|
|
Arboretum
Arboretum is a mixed reality chat app that bridges the digital and natural worlds, transforming the city of Zurich into a living network of conversations with its trees. 80,000 trees of Zurich become an interactive entities, blending real-world data with imaginative storytelling. Powered by AI and enriched by scientific and local insights, Arboretum invites users to experience the urban landscape in a new way—where nature speaks back, and every tree has a story to tell. It's a digital art experience that redefines our connection to the environment, turning Zurich's greenery into a vibrant tapestry of dialogue and discovery.
2024-11-28
|
|
|
The Open-Source Toolkit for Building AI Agents
Curated frameworks, tools, and libraries every developer needs to build functional and efficient AI agents
2025-01-12
|
|
|
Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?
Human-in-the-loop (HIL) systems have emerged as a promising approach for combining the strengths of data-driven machine learning models with the contextual understanding of human experts. However, a deeper look into several of these systems reveals that calling them HIL would be a misnomer, as they are quite the opposite, namely AI-in-the-loop (AI2L) systems, where the human is in control of the system, while the AI is there to support the human. We argue that existing evaluation methods often overemphasize the machine (learning) component's performance, neglecting the human expert's critical role. Consequently, we propose an AI2L perspective, which recognizes that the human expert is an active participant in the system, significantly influencing its overall performance. By adopting an AI2L approach, we can develop more comprehensive systems that faithfully model the intricate interplay between the human and machine components, leading to more effective and robust AI systems.
Sriraam Natarajan, Saurabh Mathur, Sahil Sidheekh, Wolfgang Stammer, Kristian Kersting