updates https://www.imperial.ac.uk/news/268473/generous-donation-advance-ai-mathematics/ https://www.imperial.ac.uk/news/261693/launching-nightingale-ai-new-foundation-world/
A multi modal foundation world model for health that is trained on millions of healthcare records, life science databases and the world's scientific knowledge.
Transform your clinical trials with our intelligent AI platform! We're building specialized assistants to cut patient-recruitment time by 60% and ...
Home
AI
Data Center
Driving
Gaming
Pro Graphics
Robotics
Healthcare
Startups
AI Podcast
NVIDIA Life.
The AI Makers: NVIDIA Partners in UK Advance Physical and Agentic AI, Robotics, Life Sciences and More,.,
September 16, 2025 by Anthony Hills
The U.K. is driving investments in sovereign AI, using the technology to advance industries like manufacturing, life sciences and more.
During NVIDIA founder and CEO Jensen Huang’s visit to the U.K. this week, NVIDIA highlighted how it is working with a broad ecosystem of AI makers across the nation on applications in physical and agentic AI, robotics and healthcare.
Such partner advancements support the
U.K.’s AI Action Opportunities Plan, published earlier this year, which includes these key pillars:
Infographic that includes three pillars of the U.K.’s AI Action Opportunities Plan: 1) Invest in the foundations of AI. The U.K. needs world-class computing and data infrastructure, access to talent and regulation. 2) Push hard on cross-economy AI adoption. The public sector should rapidly pilot and scale AI products and services, and encourage the private sector to do the same. 3) Position the UK to be an AI maker, not an AI taker. The U.K. should aim to have national champions at critical layers of the AI stack so the U.K. benefits economically from AI advancement and has influence on future AI’s values, safety and government.
Advancing the UK Technology Ecosystem
Work to build the U.K.’s AI foundation has already begun, with support from the nation’s rich research and startup ecosystem along with technology leaders.
Funded by U.K. Research and Innovation and built on NVIDIA Grace Hopper Superchips, Isambard-AI — the U.K.’s most powerful AI supercomputer based at the University of Bristol, which launched in July — is accelerating national projects including:
UK-LLM, a large language model project developed by University College London, Bangor University and NVIDIA. UK-LLM uses NVIDIA Nemotron reasoning models to support national languages like Welsh, as well as English, to improve public service delivery in sectors like healthcare and education.
Nightingale AI, a sovereign, multimodal health foundation model led by Imperial College London and trained on U.K. and US health data, which is designed to be used for numerous health applications including earlier diagnoses and personalized care.
PolluGen, a new high-resolution pollution dispersion model developed by the University of Manchester, using NVIDIA CorrDiff and Earth-2 Studio. The model can use regional health and other data to help inform citizens and policymakers of air-quality impacts.
The Ultrasound Foundation Model, led by researchers at Queen Mary University of London. The model is built for ultrasound imaging, focusing on rheumatoid arthritis patient analysis and creating a reproducible, publicly accessible AI model for medical imaging.
Gen Model in Ego-Sensed World, led by researchers at the University of Bristol, is analyzing visual data from more than 900 participants to train an AI model to better understand everyday tasks. The AI model could help predict future real-world interactions and support memory to aid independent living for dementia patients.
Electrostatics-aware foundation models, developed by researchers at the University of Cambridge in collaboration with NVIDIA. These are being trained as the first foundation models for atomic interactions that understand electrostatics in chemistry at the atomic level. To do this, the researchers are using more than 200 million molecular and material structures from the OMOL and OMAT databases with NVIDIA’s cuEquivariance library. The model will allow scientists to simulate materials and molecules that were previously too large or complex to handle.
In addition, SCAN — a technology solutions provider with a strong focus on community, education and innovation — is collaborating with NVIDIA to address the growing AI skills gap across the U.K. through NVIDIA Deep Learning Institute courses and SCAN Springboard U.K., a community-driven initiative designed to foster peer-to-peer learning, market awareness, and mass training in AI and specialized workloads.
AI for Robotics
NVIDIA announced separately today it is collaborating with techUK, alongside educational autonomous systems leader Quanser and training provider QA, to strengthen the U.K.’s robotics and AI ecosystem.
NVIDIA is also working with other leading U.K. robotics leaders to advance industries with physical AI.
Extend Robotics is accelerating safe, scalable robot deployment in vehicle manufacturing by combining extended reality-based teleoperation and advanced training systems — powered by NVIDIA Jetson AGX Orin modules, the NVIDIA Isaac Lab framework and NVIDIA Isaac GR00T models — enabling rapid skill acquisition and boosting safety and productivity.
Humanoid is developing a modular humanoid robot called HMND 01 for general tasks in warehouses and retail spaces. The robot is designed for seamless integration with human environments.
Materials Innovation Factory at the University of Liverpool is using NVIDIA tools and libraries to train a foundations model to predict material properties, as well as train robot scientists using NVIDIA Jetson Orin Nano modules to test these hypotheses within a fully automated lab environment.
The National Robotarium, a U.K. hub for robotics innovation, is using NVIDIA robotics and AI frameworks to support cutting-edge, practical research and help early-stage robotics businesses grow.
Opteran is creating autonomy algorithms for robots that mirror how the brains of insects and animals process information, harnessing knowledge on 600 million years of evolution to make robotic systems as robust and efficient as nature.
Oxa is creating full-stack AI self-driving software for industrial and commercial fleets with the NVIDIA DRIVE platform. The software works in all weather and locations — even where GPS is unreliable. Through its collaboration with NVIDIA, Oxa is able to generate vast amounts of diverse and realistic synthetic data to support training and validation — significantly accelerating the development and deployment of its solutions.
Wayve is pioneering end-to-end deep learning for autonomous driving. Its next-generation AV2.0 Platform enables vehicles to quickly and safely adapt its driving intelligence to new, unseen environments without needing expensive sensors and high-definition maps.
AI for Life Sciences
Many U.K.-based life sciences companies are using NVIDIA technologies to take an AI-first approach to drug discovery, simulating therapies and drug design to achieve faster treatment testing.
Basecamp Research’s BaseData — a proprietary evolutionary dataset that’s 10x larger than comparable public sources — is now powering a new generation of large foundation models across diverse biological data types, accelerating the development of curative, programmable medicines.
U.K. CEiSRI — the U.K. Centre of Excellence for In-Silico Regulatory Science and Innovation, headquartered at the University of Manchester — is developing complex digital twins with NVIDIA technologies to test new treatments on large and diverse patient populations.
Isomorphic Labs has built a leading AI drug design engine comprising foundational AI models that can work across multiple therapeutic areas and drug modalities.
Peptone is pioneering a new class of safer, more effective medicines by applying its physics-driven AI platform to unlock the therapeutic potential of the entire proteome, with a focus on historically “undruggable” intrinsically disordered proteins.
Latent Labs’ generative AI model, Latent-X, allows scientists to create and test therapeutic molecules in silico, speeding up drug design for researchers.
Relation Therapeutics offers a foundational AI platform for target drug discovery, integrating lab-in-the-loop experimentation to understand disease biology and accelerate the discovery and development of new therapies.
Hologen AI, a spinout with cofounders from University College London and King’s College London, represents a new breed of AI-native companies — ones harnessing the power of AI to model complex human biology and medical interventions with high precision, making new drugs available for patients rapidly and at lower cost.
Oxford Nanopore is delivering information-rich, rapid, affordable and accessible molecular information — such as DNA and RNA sequence data — to scientific researchers, as well as users in clinical, biopharma and applied industrial communities.
Agentic and Generative AI Innovations
AI model builders and startups are working with NVIDIA to transform the U.K. technology sector with agentic and generative AI tools that advance productivity, from financial large language models to AI voice agents.
Aveni created a financial LLM using the NVIDIA NeMo software suite to power its next-generation agentic framework that can interact with live financial systems, communicate with customers and advise on risk outcomes while ensuring compliance, transparency and control.
ElevenLabs develops AI voice technology that generates natural, ultrarealistic speech in over 70 languages using NVIDIA software and NVIDIA DGX B200 systems. Its models power real-time conversational agents, localization, storytelling and accessibility tools for people who have lost their voices, in addition to voicing audiobooks and animating video game characters.
PolyAI deployed advanced conversational AI agents using NVIDIA Riva automatic speech recognition NVIDIA NIM microservices. The AI agents automate customer support, speak naturally over the phone and handle complex tasks such as authentication, order management, billing and reservations on a massive scale.
Recraft is producing state-of-the-art image generation and editing models, built with advanced design capabilities to support professional creative workflows. Recraft is using the NVIDIA TensorRT software development kit, enabling users to generate and edit images and graphics to speed workflows such as producing marketing materials, generating product mockups and editing visual content.
Speechmatics developed speech-to-text software using NVIDIA Dynamo-Triton and NVIDIA cuDNN software. Its automatic speech recognition software lets businesses and developers convert spoken language into written text, with support for dozens of languages.
Synthesia built an enterprise-focused AI video platform using NVIDIA Dynamo-Triton and other NVIDIA software. With the platform, businesses create professional-quality training, marketing, sales and customer support videos from text, using AI avatars and voiceovers in over 140 languages.
Learn more about how NVIDIA is bolstering Europe’s technology ecosystem.
Categories: Data Center | Generative AI
Tags: Artificial Intelligence | Customer Stories | Deep Learning Institute | Economic Development | Education | Events | Healthcare and Life Sciences | High-Performance Computing | Industrial and Manufacturing | Isaac | Jetson | NVIDIA DGX | NVIDIA in Europe | NVIDIA NeMo | NVIDIA NIM | Physical AI | Riva | Robotics | Simulation and Design | Social Impact | Sovereign AI | TensorRT
Subscribe Widget
Recommended for You
Faster Forecasts: NVIDIA Launches Earth-2 NIM Microservices for 500x Speedup in Delivering Higher-Resolution Simulations..
NVIDIA Earth-2 Features First Gen AI to Power Weather Super-Resolution for Continental US
Staying in Sync: NVIDIA Combines Digital Twins With Real-Time AI for Industrial Automation
Taiwan Electronics Giants Drive Industrial Automation With NVIDIA Metropolis and NIM
Clear Skies Ahead: New NVIDIA Earth-2 Generative AI Foundation Model Simulates Global Climate at Kilometer-Scale Resolution
Post navigation
Reaching Across the Isles: UK-LLM Brings AI to UK Languages With NVIDIA Nemotron
Trained on the Isambard-AI supercomputer, a new model developed by University College London, NVIDIA and Bangor University taps NVIDIA Nemotron open-source techniques and datasets to enable AI reasoning for Welsh and other UK languages for public services including healthcare, education and legal resources.
September 13, 2025 by Kari Briski
Share
Celtic languages — including Cornish, Irish, Scottish Gaelic and Welsh — are the U.K.’s oldest living languages. To empower their speakers, the UK-LLM sovereign AI initiative is building an AI model based on NVIDIA Nemotron that can reason in both English and Welsh, a language spoken by about 850,000 people in Wales today.
Enabling high-quality AI reasoning in Welsh will support the delivery of public services including healthcare, education and legal resources in the language.
“I want every corner of the U.K. to be able to harness the benefits of artificial intelligence. By enabling AI to reason in Welsh, we’re making sure that public services — from healthcare to education — are accessible to everyone, in the language they live by,” said U.K. Prime Minister Keir Starmer. “This is a powerful example of how the latest AI technology, trained on the U.K.’s most advanced AI supercomputer in Bristol, can serve the public good, protect cultural heritage and unlock opportunity across the country.”
The UK-LLM project, established in 2023 as BritLLM and led by University College London, has previously released two models for U.K. languages. Its new model for Welsh, developed in collaboration with Wales’ Bangor University and NVIDIA, aligns with Welsh government efforts to boost the active use of the language, with the goal of achieving a million speakers by 2050 — an initiative known as Cymraeg 2050.
U.K.-based AI cloud provider Nscale will make the new model available to developers through its application programming interface.
“The aim is to ensure that Welsh remains a living, breathing language that continues to develop with the times,” said Gruffudd Prys, senior terminologist and head of the Language Technologies Unit at Canolfan Bedwyr, the university’s center for Welsh language services, research and technology. “AI shows enormous potential to help with second-language acquisition of Welsh as well as for enabling native speakers to improve their language skills.”
This new model could also boost the accessibility of Welsh resources by enabling public institutions and businesses operating in Wales to translate content or provide bilingual chatbot services. This can help groups including healthcare providers, educators, broadcasters, retailers and restaurant owners ensure their written content is as readily available in Welsh as they are in English.
Beyond Welsh, the UK-LLM team aims to apply the same methodology used for its new model to develop AI models for other languages spoken across the U.K. such as Cornish, Irish, Scots and Scottish Gaelic — as well as work with international collaborators to build models for languages from Africa and Southeast Asia.
“This collaboration with NVIDIA and Bangor University enabled us to create new training data and train a new model in record time, accelerating our goal to build the best-ever language model for Welsh,” said Pontus Stenetorp, professor of natural language processing and deputy director for the Centre of Artificial Intelligence at University College London. “Our aim is to take the insights gained from the Welsh model and apply them to other minority languages, in the U.K. and across the globe.”
Tapping Sovereign AI Infrastructure for Model Development
The new model for Welsh is based on NVIDIA Nemotron, a family of open-source models that features open weights, datasets and recipes. The UK-LLM development team has tapped the 49-billion-parameter Llama Nemotron Super model and 9-billion-parameter Nemotron Nano model, post-training them on Welsh-language data.
Compared with languages like English or Spanish, there’s less available source data in Welsh for AI training. So to create a sufficiently large Welsh training dataset, the team used NVIDIA NIM microservices for gpt-oss-120b and DeepSeek-R1 to translate NVIDIA Nemotron open datasets with over 30 million entries from English to Welsh.
They used a GPU cluster through the NVIDIA DGX Cloud Lepton platform and are harnessing hundreds of NVIDIA GH200 Grace Hopper Superchips on Isambard-AI — the U.K.’s most powerful supercomputer, backed by £225 million in government investment and based at University of Bristol — to accelerate their translation and training workloads.
This new dataset supplements existing Welsh data from the team’s previous efforts.
Capturing Linguistic Nuances With Careful Evaluation
Bangor University, located in Gwynedd — the county with the highest percentage of Welsh speakers — is supporting the new model’s development with linguistic and cultural expertise.
Welsh translation of: “The aim is to ensure that Welsh remains a living, breathing language that continues to develop with the times.” — Gruffudd Prys, Bangor University
Prys, from the university’s Welsh-language center, brings to the collaboration about two decades of experience with language technology for Welsh. He and his team are helping to verify the accuracy of machine-translated training data and manually translated evaluation data, as well as assess how the model handles nuances of Welsh that AI typically struggles with — such as the way consonants at the beginning of Welsh words change based on neighboring words.
The model, as well as the Welsh training and evaluation datasets, are expected to be made available for enterprise and public sector use, supporting additional research, model training and application development.
“It’s one thing to have this AI capability exist in Welsh, but it’s another to make it open and accessible for everyone,” Prys said. “That subtle distinction can be the difference between this technology being used or not being used.”
Deploy Sovereign AI Models With NVIDIA Nemotron, NIM Microservices
The framework used to develop UK-LLM’s model for Welsh can serve as a foundation for multilingual AI development around the world.
Benchmark-topping Nemotron models, data and recipes are publicly available for developers to build reasoning models tailored to virtually any language, domain and workflow. Packaged as NVIDIA NIM microservices, Nemotron models are optimized for cost-effective compute and run anywhere, from laptop to cloud.
Europe’s enterprises will be able to run open, sovereign models on the Perplexity AI-powered search engine.
Get started with NVIDIA Nemotron.
Categories: Deep Learning | Generative AI
Tags: Artificial Intelligence | Education | NVIDIA NIM | Social Impact | Sovereign AI | Synthetic Data Generation
Load Comments
Subscribe Widget
Recommended for You
Faster Forecasts: NVIDIA Launches Earth-2 NIM Microservices for 500x Speedup in Delivering Higher-Resolution Simulations
NVIDIA Earth-2 Features First Gen AI to Power Weather Super-Resolution for Continental US
Staying in Sync: NVIDIA Combines Digital Twins With Real-Time AI for Industrial Automation
Taiwan Electronics Giants Drive Industrial Automation With NVIDIA Metropolis and NIM
Clear Skies Ahead: New NVIDIA Earth-2 Generative AI Foundation Model Simulates Global Climate at Kilometer-Scale Resolution
Post navigation
Paint It Blackwell: GeForce RTX 5080 SuperPOD Rollout Begins
Kick off the biggest cloud upgrade with three new games, including the launch of ‘Borderlands 4,’ with a new membership offer.
September 10, 2025 by GeForce NOW Community
Share
GeForce NOW Blackwell RTX 5080-class SuperPODs are now rolling out, unlocking a new level of ultra high-performance, cinematic cloud gaming.
GeForce NOW Ultimate members will see GeForce RTX 5080 performance arriving to a server near them, enabling even richer experiences in blockbuster titles like DUNE: Awakening, Borderlands 4, Hell Is Us, Dying Light: The Beast, Cronos: The New Dawn, Clair Obscur: Expedition 33 and more.
They all come with breathtaking graphics and lowest-latency gameplay, thanks to NVIDIA DLSS 4 technology and next-generation AI features. Experience the new Cinematic-Quality Streaming mode for stunning color and fidelity across the latest devices.
Install-to-Play on GeForce NOWLook at all the room for activities gaming.
The new Install-to-Play feature is expanding the cloud library to nearly 4,500 games for Ultimate and Performance members.
This week kicks it off with three new games, including the launch of Borderlands 4. GeForce NOW is the ultimate way to play the Borderlands franchise’s latest entry — free with the purchase of a new 12-month Ultimate membership bundle.
Make sure to follow along on GFN Thursdays for server updates.
Blackwell to the Future
GeForce RTX 5080 power on GeForce NOWGame-changer.
The future of cloud gaming has arrived. With the NVIDIA Blackwell RTX upgrade, GeForce NOW brings GeForce RTX 5080-class performance to the cloud for the first time. Ultimate members can harness DLSS 4 Multi-Frame Generation, cutting-edge AI enhancements and ultralow click-to-pixel latency, enabling up to 5K at 120 frames per second for premium, responsive gameplay.
Members will also see the GeForce NOW library instantly double. Over 2,200 Steam titles opted in by publishers for cloud streaming are hitting the cloud today, with more to come, letting members build and manage their own cloud gaming library. Alongside new Install-to-Play titles, GeForce NOW will continue to roll out ready-to-play titles each week.
Blackwell RTX rollout on GeForce NOWComing to a zone near you.
NVIDIA Blackwell RTX servers are starting to power up worldwide, so more members can start streaming with unprecedented performance on virtually any device, including PCs, Macs, Chromebooks, LG TVs (4K at 120Hz) and even Steam Decks (now up to 90 fps). Keep an eye on GFN Thursday updates and check the server rollout webpage for new regions going live.
Ultimate members will soon see GeForce RTX 5080 performance in their area, with AAA titles like DUNE: Awakening, Borderlands 4, Hell Is Us, Dying Light: The Beast, Cronos: The New Dawn, Clair Obscur: Expedition 33 and more playable at ultimate quality. Look for the new “GeForce RTX 5080 Ready” row in the app for the full list of GeForce RTX 5080-optimized games, updated weekly with fresh additions.
GeForce RTX 5080 ready games on GeForce NOWNew row, who ‘dis?
Don’t let this cloud pass by. The Blackwell RTX upgrade is ready for gamers to secure their spots — no downloads, no hardware upgrades, just next-level gaming for the same $19.99 per month. Or members can choose to subscribe to the 12-month membership for $199.99 — providing more value at less than $17 a month.
Break Free With ‘Borderlands 4’
Borderlands 4 on GeForce NOWWelcome to Border-LOL-lands.
Get ready for a blast of chaos, color and fun as Borderlands 4 launches on GeForce NOW. The galaxy’s wildest looter shooter is back, sending four new Vault Hunters on a loot-crazed rampage jam-packed with quippy dialogue and sci-fi shenanigans, all wrapped in the franchise’s signature mayhem.
Gameplay turns the dial to 11 with new double jumps, dashes, grappling hooks and air-glide moves that make every firefight a circus act. Experience a world with sprawling landscapes and nonstop dynamic events.
Build the perfect Vault Hunter with deep skill trees and use different weapons — each with unique behaviors and effects, now with a revamped loot system where every Legendary feels special. Play it solo or with up to three friends.
Play the frantic co-op looter shooter on GeForce NOW with the NVIDIA Blackwell RTX upgrade for cinematic-quality visuals, ultrafast load times and stunning performance. Enjoy NVIDIA DLSS 4-fueled graphics and low-latency gameplay streaming from GeForce RTX 5080 gaming rigs in the cloud.
Borderlands 4 membership bundle on GeForce NOWThe cloud is the best way to play.
The title lands in the cloud on Thursday, Sept. 11. Gamers who upgrade to or purchase a 12-month GeForce NOW Ultimate membership — between now and Tuesday, Sept. 25 — will get the title for free, available to play as soon as it launches. Unleash chaos across the galaxy with outrageous weapons, irreverent humor and the signature co-op action that makes this iconic looter-shooter franchise a fan favorite.
Game On
Genshin Impact latest update on GeForce NOWSet sail for moonlit mystery in Nod-Krai.
Genshin Impact “Version Luna I: Song of the Welkin Moon” is available to play instantly on GeForce NOW — no need to wait for downloads or updates. Head on a new adventure through the magical new region of Nod-Krai, where the story, exploration and battles are all shaped by the mysterious power of the moon. Play as three new characters — animal-loving Lauma, energetic Flins and inventive Aino — as they face off against rival factions, unravel secrets and wield creative new abilities in a world full of quirky creatures and vibrant islands. Plus, anniversary rewards await for everyone who jumps in.
In addition, members can look for the following:
Firefighting Simulator: Ignite (New release on Steam, Sept. 9)
Borderlands 4 (New release on Steam and Epic Games Store, Sept. 11)
Professional Fishing 2 (New release on Steam, Sept. 11)
What are you planning to play this weekend? Let us know on X or in the comments below.
Categories: Gaming
Tags: Cloud Gaming | GeForce NOW
Load Comments
Subscribe Widget
Recommended for You
Faster Forecasts: NVIDIA Launches Earth-2 NIM Microservices for 500x Speedup in Delivering Higher-Resolution Simulations
NVIDIA Earth-2 Features First Gen AI to Power Weather Super-Resolution for Continental US
Staying in Sync: NVIDIA Combines Digital Twins With Real-Time AI for Industrial Automation
Taiwan Electronics Giants Drive Industrial Automation With NVIDIA Metropolis and NIM
Clear Skies Ahead: New NVIDIA Earth-2 Generative AI Foundation Model Simulates Global Climate at Kilometer-Scale Resolution
Post navigation
Corporate Information
About NVIDIA
Corporate Overview
Technologies
NVIDIA Research
Investors
Social Responsibility
NVIDIA Foundation
Get Involved
Forums
Careers
Developer Home
Join the Developer Program
NVIDIA Partner Network
NVIDIA Inception
Resources for Venture Capitalists
Venture Capital (NVentures)
Technical Training
Training for IT Professionals
Professional Services for Data Science
News & Events
Newsr
