IKM® State of Art

K2K®: Powering the Next Generation of Sovereign AI for Cognitive Cities
Barcelona, November 2025
K2K® is redefining how cities think, act, and grow in the era of sovereign AI. With a clear vision, to build ecosystems where data, knowledge, and people work in harmony. K2K® is leading the way toward a future where AI is powerful, responsible, and locally owned.
K2K® develops advanced, sustainable neural network architectures that extract and capitalize on meaning from real-time video streams. Its sovereign-by-design approach combines cloud power with local context and control, empowering cities and communities to turn data into trusted, actionable intelligence.
Introducing IKM® VLM: A New Cognitive Layer for Cities
At the heart of K2K®’s strategy is the IKM® Vision-Language Model (VLM), the first model of its kind fully compliant with both the AI Act and General Data Protection Regulation (GDPR) and leveraging NVIDIA Blueprint for smart city AI.
Unlike traditional computer vision, this VLM doesn’t just see: it understands, describes, and contextualizes what it observes. It connects imagery with language, knowledge, and intent, unlocking a new semantic intelligence layer for cities.
• Real-time interpretation of urban life: from traffic flow to crowd behavior.
• Faster AI deployment: cutting integration time and boosting ROI.
• Seamless interoperability: fully integrated with NVIDIA’s accelerated computing stack: next-generation GPUs, NVIDIA TensorRT, NVIDIA CUDA, NVIDIA Triton Inference Server, and frameworks like NVIDIA Metropolis, NVIDIA NeMo Curator, and NVIDIA Cosmos Reason.
This synergy amplifies K2K®’s ability to transform raw video streams into structured, certified, and sovereign knowledge, enabling faster decision-making and scalable intelligence.
Turning City Data into a Living Cognitive Fabric
Every image. Every movement. Every urban event.
Through K2K®’s architecture, these elements are captured, certified, and transformed into what the company calls a “genetic heritage of information”, a living, evolving knowledge base that cities can own, protect, and monetize.
• Data is not consumed, it is regenerated.
• Cities build cognitive capital that compounds over time.
• Intelligence becomes measurable, interpretable, and actionable.
Real-World Adoption: European Cities Leading the Way
K2K®’s technology is already being adopted and tested by a growing number of forward-looking municipalities across Europe.
• Palermo (Italy), deploying IKM® VLM to strengthen urban intelligence and mobility monitoring.
• Łódź (Poland), piloting sovereign AI models to improve traffic and environmental awareness.
• Acquappesa (Italy), exploring cognitive city applications for local governance and public safety.
• Locri (Italy), testing community-scale deployments to enhance operational efficiency and resilience.
These early adopters represent a new wave of cognitive cities: urban environments where AI is implemented responsibly, owned locally, and designed to serve communities first.
From Smart Cities to Cognitive Cities
Across Europe, pioneering cities are already working with K2K® to move beyond the “smart city” paradigm toward urban neural networks, cities capable of learning, adapting, and collaborating in real time.
Every GPU, every AI agent, every model becomes a node in a shared cognitive fabric that strengthens the community’s capacity to act locally, responsibly, and sustainably.
Sovereign by Design, Built with Trust
For K2K®, AI isn’t just about performance. It’s about trust, transparency, and sovereignty.
That’s why its solutions are designed to keep data, computation, and models in the hands of the communities that generate them.
“We believe AI should serve people, not replace them. Together with NVIDIA, cities, and institutions, we are building the digital neural system of the cities of tomorrow,” said Marco De Paoli, CEO of K2K®.
About K2K®
K2K® is a pioneering company in sovereign AI for urban environments. Its mission is to build cognitive city ecosystems where data is meaningful, trusted, and locally controlled. K2K® combines cutting-edge neural network architectures with NVIDIA’s accelerated computing technologies to unlock real-time intelligence and responsible innovation.

City of Palermo Brings AI Innovation to Urban Management with K2K®
Palermo, September 30, 2025
Palermo today announces a strategic collaboration with K2K®, to enhance city operations with an advanced vision language model (VLM) customized for smart cities and spaces. This VLM is natively compliant with European regulations such as the Artificial Intelligence Act and General Data Protection Regulation.
This initiative marks a major step in Palermo’s digital transformation, improving how the city perceives, understands, and responds to daily urban challenges: from mobility and waste collection to public safety and environmental analysis.
Solving Real Urban Problems with AI
As Palermo continues its journey, the city faces growing challenges in traffic management, waste collection efficiency, and public service responsiveness. To address these issues, the municipality partnered with K2K®, whose Neural Networks Architectures integrate video AI and natural language understanding to make city data accessible and actionable in real time.
The K2K® Solution
Created with NVIDIA Blueprint for smart city AI, and Cosmos Curator on DGX Cloud, the VLM combines visual and linguistic intelligence within a single framework, bridging the gap between the physical and digital worlds.
The solution can analyse live video feeds and sensor data, with NVIDIA Metropolis, capitalizing on existing sensor infrastructure, transforming the city’s visual data into structured knowledge, allowing city operators to query urban events using natural language and receive immediate visual and data driven responses.
Through predictive analytics, Palermo’s teams can now:
• Analyse and optimize Waste Management resources, reducing trash on streets.
• Improve traffic flow and incident response times
• Make decisions based on extracted environmental conditions to anticipate maintenance and safety needs
Why Palermo Chose K2K®
This collaboration marks a strategic turning point in the digital transformation of Palermo, a city that already has a well-established IT and telecommunications system and the right level of AI maturity that this “vision” requires.
Palermo selected K2K® for its proven expertise in AI architectures for smart cities and its ability to deploy scalable, compliant, and secure systems aligned with EU regulations, including the AI Act and GDPR.
In this vision, AI compliance is not a feature but the foundation of urban infrastructure, ensuring accountability, transparency, and trust with residents.
Current Results and Next Steps
The platform has been operating on Palermo’s certified municipal cloud infrastructure, provided by Nebius, an NVIDIA Certified Cloud Provider and managed in collaboration with SISPI Sistema Palermo Innovazione S.p.A.
By integrating perception, memory, and reasoning directly into its operational core, the city is moving from data-driven management to knowledge-based governance.
Next, Palermo plans to expand AI integration across mobility planning, environmental management, and citizen engagement platforms, paving the way for a more efficient, automated, and sustainable city.
“Palermo is proud to lead the creation of a true Smart City” said Prof. Roberto Lagalla, Mayor of the City of Palermo. “By combining technological innovation with regulatory principles, we are building a future where cities serve people with intelligence, responsibility, and vision.”
“With Palermo, we are defining a new global standard for what cities can become when technology and compliance advance together,” said Marco De Paoli, CEO of K2K®. “This is not simply about implementing another smart city solution, it’s about equipping cities with capabilities that allow them to see, understand, and act in real time while protecting citizens’ rights and trust. Palermo is showing how digital sovereignty and responsible AI can move forward hand in hand.”
About Palermo
Palermo, the capital of Sicily, is a historic Mediterranean hub of culture, innovation, and transformation.
A pioneer since the 1990s in the computerization of its administrative processes, the City has continued to invest in the transformation of its bureaucratic machinery, drawing on the expertise and services of its technology partner, SISPI, with which it has launched an ambitious digital modernization program in recent years, integrating its rich cultural heritage with future-oriented infrastructure investments.
Palermo's strategy emphasizes sustainability, inclusion, and technological sovereignty, making it a model for medium-sized European cities committed to the responsible adoption of artificial intelligence.
About K2K®
K2K® is a pioneer in cognitive artificial intelligence architectures, enabling urban environments and organizations to transform video and sensor data into actionable Knowledge, supporting the evolution of Smart Cities and Smart Spaces across the World.
About NVIDIA
NVIDIA is a global leader in accelerated computing and AI infrastructure. Its platforms power the world’s most advanced AI systems and digital twins, enabling cities, industries, and governments to rethink the future of innovation.

There are places where the future is not imagined: it is shaped.
At the Smart City Expo World Congress 2025, we will present the state of the art of our technology for smart spaces as living organisms capable of perceiving, remembering, and reasoning.
A pulsating network of connections, data, and ethics that transforms urban space into a sensitive, sustainable, and conscious system.
With K2K® Neural Network Architectures, technology becomes language, complexity turns into harmony, and innovation takes shape in the very rhythm of metropolitan life.
By integrating perception, memory, and reasoning into its operational core, the city evolves from data-driven management to knowledge-based governance.
See you in Barcelona, where cities learn to turn space into knowledge.
Find K2K® at the heart of the Expo:
DELL NVIDIA | Gran Via, Hall 2, Level 0, Street B, Stand 131
MINDWARE | Gran Via, Sala 3, Livello 0, Via C, Stand 182
DELOITTE | Gran Via, Hall 2, Level 0, Street D, Stand 130
Smart City Expo World Congress 2025 | 4-6 November | Barcelona

Al Transport Innovation Forum
Urban innovation takes shape through the virtuous convergence of institutions, enterprises, and research.
In a world marked by perpetual transformation, the response to metropolitan challenges lies in intelligent infrastructures, adaptive services, and technologies capable of perceiving, learning, and acting in real time.
Sophisticated neural architectures are redefining how we approach urban complexity: Agentic AI and Physical AI are transforming the urban environment into a distributed mind, able to harmonize complexity with intelligence, efficiency, and sustainability.
The dynamic exploration of urban scenarios enables us to anticipate the impact of every decision, shaping cities that evolve in step with the needs of their communities, through a continuous dialogue between technology and territory.
Al Transport Innovation Forum | LITEXPO | 15-16 October, Vilnius

The AI Ecosystem That Accelerates Innovation
The AI ecosystem is evolving into a distributed cognitive entity, a form of collective intelligence capable of perceiving, learning, and acting with contextual awareness.
It is a synergistic interplay of expertise, data, and vision, transforming innovation into a living, responsive, and reflective organism.
Within this emergent paradigm, research converges with enterprise, creativity intertwines with engineering, and ideas crystallize into cognitive architectures.
Innovation is a masterful orchestration of heterogeneous intelligences, engaging in refined dialogue and mutually elevating one another through shared enrichment.
Fabbrica ITALIA | October 3rd, Bologna

Destination AI
With each passing day, we contribute to the orchestration of tomorrow’s Technological Paradigm, elevating data into discerning insight, harnessing innovation as a strategic catalyst, and translating vision into action.
Innovation manifests as a concrete force, shaped by the decisions we make in the present.
The Future is not a distant horizon to be awaited, it is a construct we design, through foresight, experties, and an unwavering pursuit of excellence.
Destination AI Tour | 23 September, Rome

Cities are not just spaces to inhabit, but visions to be realized.
Their evolution reflects the ingenuity and foresight of those who design them.
With great enthusiasm, we are integrating a powerful framework that enables the creation, testing, and optimization of AI agents within SimReady digital twins, in conjunction with the NVIDIA Omniverse Blueprint for Smart Cities.
Real-time exploration of urban scenarios anticipates the impact of every decision, shaping dynamic city ecosystems. Infrastructure, mobility, and services are precisely modeled around the needs of the community.
Agentic AI and Physical AI transform the urban environment into a distributed, responsive mind capable of harmonizing metropolitan complexity with intelligence and sustainability.
NVIDIA and K2K® embrace this ambitious challenge, helping define a new paradigm: cities that think, learn, and evolve.
Smarter public spaces, more seamless services, and a daily life enriched by deep, sensitive interaction between people, environment, and innovation.
Thanks to this synergy, the urban fabric comes alive with intelligence and vision.

Urban Vision AI Enters a New Era with K2K®: City-Scale Video Curation Complete for VLM Fine-Tuning Using NVIDIA DGX Cloud
A breakthrough in visual AI at city scale has just been realized.
K2K® is one of the early adopters of the newly announced NVIDIA Omniverse Blueprint for Smart City AI. to optimize operations AI agents and digital twins for cities. The blueprint provides the complete software stack needed to efficiently develop AI agents and digital twins at scale.
K2K® has also successfully launched the curation of a vast urban video dataset to fine-tune next-generation Vision Language Models (VLMs) optimized for the NVIDIA AI Blueprint for video search and summarization (VSS) workloads. This milestone combines cutting-edge data curation infrastructure with powerful AI training services on NVIDIA DGX Cloud.
The curated data covers city life across a full set of diverse conditions: traffic density, lighting variations, weather events, and pedestrian flow, reflecting the rich complexity of real-world urban dynamics. The initiative lays the groundwork for intelligent systems capable of perceiving, reasoning, and interacting with the physical environment in real time.
From Raw Video to Real Intelligence
The core challenge in building high-performance vision AI agents lies not only in computing power, but in the quality and scale of AI training data available. This project addresses that by curating city-scale video footage using advanced pipelines designed for regulatory compliance, privacy-preserving transformations, and multimodal annotation.
Once curated, the video data is processed in DGX Cloud using fine-tuning microservices optimized for NVIDIA AI Blueprints. This stack accelerates the development of highly interactive, perceptive visual AI agents capable of powering a new class of smart city services, from real-time traffic summarization to multimodal urban analytics powered by K2K®’s Neural Networks Architectures.
Training Vision AI Agents for the Real World
This work enables a new generation of VLMs fine-tuned specifically for dense, live video environments. These models are built for low-latency video understanding and retrieval, key to real-time analysis such as live camera search, scene summarization, and generative events reporting.
Aligned with the NVIDIA AI Blueprint for Video Search and Summarization (VSS), the project demonstrates how purpose-trained VLMs can serve as foundational components for digital agents operating across complex dynamic physical spaces. Whether deployed at intersections, transportation hubs, or public venues, these agents are capable of answering questions, generating summaries, and surfacing critical information directly from video feeds.
DGX Cloud: A Platform for Scalable Urban AI
The initiative showcases the synergy of high-performance AI infrastructure and modular data engineering. DGX Cloud streamlined the model, fine-tuning with scalability and speed, eliminating the traditional bottlenecks of compute-bound training cycles. NVIDIA provides the backbone for compliant, high-throughput video ingestion, enrichment, and labeling—accelerating the path from raw footage to high-value AI-ready data.
A Foundation for the Next Phase of Urban Intelligence
This effort is the first of several strategic steps aimed at operationalizing sovereign AI for cities, architectures of Neural Networks that are not only powerful and accurate, but also auditable, explainable, and aligned with public values.
The NVIDIA Omniverse Blueprint for Smart City AI provides a framework that focuses on training AI to perceive and respond in complex scenarios, testing the AI in a digital twin, and deploying the AI through AI agents. Next, K2K® plans to explore the use of digital twins for simulating and testing AI agents before deployment.
The fine-tuned VLM emerging from this pipeline is designed to support a broad range of use cases, from traffic flow optimization to public safety insights, infrastructure resilience, and emergency response.
By abstracting visual reasoning into adaptable services, this initiative empowers both public and private stakeholders to unlock the full potential of their video assets, with full compliance, responsibly, and at scale.

Redefining Urban Evolution with Gen Al
Be Genetic
Learn how video Al agents analyze thousands of video streams in real time, leveraging NVIDIA GPUs and NVIDIA Al Blueprint for video search and summarization to transform complex data into actionable insights.
This session will showcase how Palermo is exploiting cutting-edge technology to drive the digital industrial revolution in urban settings, extracting, managing, and capitalizing on data to make cities smarter.
NVIDIA GTC2025, San Jose

Enhance Visual Understanding with Generative AI
Video GenAI is revolutionizing the way systems learn, adapt, and operate in real-time.
This technology opens up new possibilities in video stream analysis, extracting insights that were previously unreachable.
Thanks to advanced tools like Neural Ordinary Differential Equations (ODE) and State Space Models (SSM), it is possible to overcome complex challenges, unlocking the full potential of VLMs in real-world scenarios.
These innovations are transforming Smart Cities, making real-time video analysis a key resource for the future.
NVIDIA Webinar January 22, 2025

IKM® Technologies
Data Sheet
Smart City Expo World Congress 2024
Generative Neural Network Architectures
for the Management of Complex Processes,
the Genesis of Information.

IKM® Neural Networks Enhanced with NVIDIA NIM: A New Era of Smart City Solutions
K2K® is proud to announce that IKM® Neural Networks Architectures now include NVIDIA NIM microservices, part of the NVIDIA AI Enterprise software platform, and vision language models (VLMs) to power smart city applications with advanced video generative AI. This integration is set to elevate the neural networks' capabilities in traffic and waste management, public safety, and environmental analysis, enabling cities to efficiently manage resources and improve urban life.
1. IKM® Global VQA
IKM® Neural Networks, powered by NVIDIA NIM microservices, supercharge real-time analytics across multi-camera streams with high precision. City operations teams can obtain instant answers to natural language queries, as well as engage in multi-turn conversation spanning multiple data sources and correlate images to further refine query results, allowing for immediate and highly specific insights into issues such as roadworks, crowd density, and environmental hazards. This breakthrough capability enables faster, more adaptive decision-making in critical urban situations, which can transform the way cities respond to challenges.
2. OVCR® Traffic Management
The OVCR® Traffic Management system provides real-time vehicle tracking, congestion analysis, and speed analysis. This data allows city planners to optimize traffic flow, enhance road safety, and respond quickly to incidents. The neural networks’ capabilities also give traffic managers a complete, real-time overview of traffic patterns and road conditions, making cities safer and more efficient.
3. IKM® Waste Management
With NVIDIA NIM microservices, IKM® Neural Networks analyze video streams of waste bin fill levels and surrounding cleanliness. Real-time insights into illegal dumping or full waste bins allow cities to better plan waste collection and maintain cleaner environments, reducing operational costs and contributing to urban aesthetics.
K2K® is helping set a new benchmark for smart cities, harnessing the power of neural networks, VLMs, and NVIDIA AI Blueprints to create cleaner, safer urban environments.
K2K® is excited to drive the future of smart cities and deliver innovations that improve urban life for all residents using NVIDIA AI.

Transforming Smart Cities with IKM® Technology powered by NVIDIA AI Blueprints and Metropolis
K2K® is empowering cities with advanced video search, summarization and video generative AI capabilities, powered by NVIDIA’s AI software stack and NVIDIA AIBlueprints, which are designed to tackle complex urban challenges by delivering real-time insights that help manage resources, streamline operations, and ensure public safety in urban environments.
NVIDIA AI Blueprints are reference workflows for generative AI use cases, built with NVIDIA NIM microservices as part of the NVIDIA AI Enterprise software platform. The new AI Blueprint for video search and summarization helps developers like K2K leverage NVIDIA Metropolis to create a diversity of AI agents that can perform visual understanding of activities within video and to build smart city services.
By integrating NVIDIA AI Blueprints, part of NVIDIA AI Enterprise, IKM® Technology brings real-time, intelligent insights to smart cities. Through state-of-the-art neural networks and video genAI, the IKM® Neural Networks Architectures can support various urban applications, from optimizing traffic flow to enhancing waste management and analyzing environmental conditions. These enhancements enable smart cities to make informed, knowledge-driven decisions for managing urban resources efficiently and effectively.
Users can specify prompts and events that the system will analyze and summarize, giving city operators immediate access to information on incidents like traffic blockages, large gatherings, and environmental concerns.
This not only allows for a quicker response to urban developments but also significantly boosts city management and situational awareness.
This collaboration with NVIDIA brings exceptional scalability and adaptability to IKM® Neural Networks, enabling cities to harness the power of real-time insights and alerts for a smarter and safer urban experience. K2K® is helping set new standards in smart city technology, making cities not only more connected but also more resilient and sustainable.
See K2K® in action at Smart City Expo World Congress in Barcelona, November 5-7th. Find us demoing in Dell Technology’s pavilion Gran Via, Hall 3, Level 0, Street D, Stand 101 and the AMSYS-Lenovo booth Gran Via, Hall 3, Level 0, Street C, Stand 41.

Al Gets Physical: New NVIDIA NIM Microservices Bring Generative Al to
Digital Environments
Generative physical Al NIM microservices - and NVIDIA Metropolis reference workflows - are helping create intelligent, immersive work environments.
July 29, 2024

Smart Spaces Virtual Summit
Neural Networks, Video Knowledge Management & Management of Information
June 21, 2023

Truth Machine
With the graphical processing units (GPUs), numerous algorithms have been adapted for parallel computing, achieving execution times that are approaching real time. Specifically for emotion recognition from facial images, these computational enhancements have ushered in the second class of approaches, neural networks — and in particular, Convolutional Neural Networks (CNNs).
