Can text-to-image models count what they create? 🖼️🔢 In this ELLIOT Research Spotlight 🔬, we highlight QUOTA, an optimisation framework that helps AI generate the right number of objects across unseen domains, without retraining for each one. Paper + code in the comments 🔗

How can AI vision work better in low light or changing environments? 📷 In this video, Niccolò Biondi (UNITN) presents PEPR, a method that combines RGB and event-based camera data to improve robustness in real-world conditions. 👀 🔗 Watch the video: www.youtube.com/watch?v=AxVP...

PEPR: Event-Based Predictive Regularization for Domain Generalization by Niccolò Biondi (UNITN)

YouTube video by ELLIOT Project

youtube.com

Food recognition is more than naming a dish. 🍽️ In this interview, Eric Verdaguer, Co-Founder and CEO of LogMeal, explains how AI can identify ingredients, estimate quantities and support professionals in healthcare, sports, wellness and food services. Watch now. 🎬

Our homepage has a fresh new look! 🌐 Explore our new “Latest Updates” section, featuring project news, events, and scientific outputs (publications, datasets, software & models). Tracking open science has never been easier! Explore our website here: www.elliot-ai.eu

How can AI combine specialised models without losing what each one does best? 🧠 In this ELLIOT workshop interview, Joost van de Weijer (CVC-CERCA) explains model merging and how it can support collaboration when data cannot be shared in one place. Watch now. 🎬

ELLIOT Research Spotlight 🔬 Huge congratulations to the EPFL for their forward-looking work on Test-Space Training! This brings brilliant localised intelligence to AI via self-supervision. Pushing boundaries for European open science! 🚀🤝 Explore the results and overview video: tst-vision.epfl.ch

How can AI learn everyday actions from a person’s point of view? 👀 In this ELLIOT interview, @dimadamen.bsky.social (University of Bristol) explains why first-person vision matters and why translating human actions into language remains a major challenge for multimodal AI. Link in comments 👇

How can AI better understand 3D driving scenes? 🚗 In this ELLIOT Research Spotlight 🔬, we highlight LOSC from @valeoai.bsky.social: a method for open-vocabulary LiDAR segmentation that helps assign meaning to 3D point clouds, beyond fixed object categories. Paper + code in comments 👇

Finding the right words to talk to AI can be tough! 🧠 This is why Tom Zehle from @ellisinsttue.bsky.social created Promptolution, a modular framework that automates prompt optimisation. Watch the video below to discover how it easily boosts LLM performance! 🚀🎬

AI systems that understand human behaviour can support new digital assistants, but they also raise risks around manipulation and impersonation 🧠. In this ELLIOT workshop interview, Ioannis Patras (Queen Mary University of London & Tavus) explores safe and responsible use of AI. Watch now 👀

Happy AI Appreciation Day! 🤖✨ Today, we celebrate the incredible ways AI is improving our lives, from climate modelling to real-world medicine. At ELLIOT, we’re so proud of our 34 partners building open, responsible technology that Europe can truly trust. Let’s innovate together! 🤝

How can AI help us take more memorable photos? 📸 In our latest Poster Session video, Francesco Laiti (University of Trento) presents MemCoach: a training-free multimodal model that gives natural language feedback to improve image memorability. 🎬 Full video here: www.youtube.com/watch?v=mvtn...

AI coaching for capturing more memorable photographs by Francesco Laiti (UNITN)

YouTube video by ELLIOT Project

youtube.com

Time for another ELLIOT Buzzword! ✍️ Today it's "Robust Generalisation". Think of it as training AI to handle a sudden storm, not just sunny weather. It means our open models stay smart and reliable even when conditions shift or reality gets messy! 🚗⛈️✨

Last week, ELLIOT partners visited the Barcelona Supercomputing Center during the consortium meeting. A great chance to see the infrastructure powering Europe’s AI research and connect our discussions with the computing capacity behind multimodal foundation models. 🤖✨

Ready for a research stay in beautiful Ljubljana? Collaborate with the JSI ELLIOT team in Slovenia on cutting-edge multimodal auto-fine-tuning and AI debiasing. Help us make adapting large models cheaper, faster and fairer for everyone! 🔗 Apply here: www.elliot-ai.eu/mobility-pro...

Exciting news! 🚀 ELLIOT supports the 10th CONVERSATIONS Symposium on human-centred AI in Amsterdam (23-25 Nov)! 🤖✨ Call for Papers & Reviewers is open! Submit by 5 Sept 2026. Let's shape trustworthy AI together! 🤝 🔗 Know more here: elliot-ai.eu/events/conve... @themis-trust.bsky.social

🚀 Happening now in Barcelona! The Workshop on Multimodal Foundation Models: From Research to Innovation is bringing together researchers, industry experts and European AI initiatives to discuss the future of multimodal AI. A great start to a day of discussion! 🤝

That’s a wrap on the ELLIOT consortium meeting in Barcelona! Huge thanks to CVC-CERCA for hosting our 34 partners from 13 countries. Two days of reviewing progress and aligning the next steps of trustworthy AI research. 🤝🤖

How can meal images become healthcare intelligence? 🍽️🤖 Join Eric Verdaguer, Co-Founder & CEO of LogMeal, at the Workshop on Multimodal Foundation Models, where he will explore AI-powered nutrition and food-waste monitoring in healthcare settings. There is still time to join us online on July 1! 👇

We are excited to welcome Lukas Fischer to the panel at the Workshop on Multimodal Foundation Models! As Head of Applied Research at NXAI, he will bring an applied research & industry perspective on efficient foundation models, multimodal AI & trustworthy AI. 🔗 elliot-ai.eu/events/multi... @ellis.eu

We are excited to welcome Jordina Torrents Barrena to the panel at the Workshop on Multimodal Foundation Models! Senior AI Manager & Principal AI Architect at HP Inc., she will bring an industry perspective on moving AI research towards real-world innovation. 🔗 elliot-ai.eu/events/multi... @ellis.eu

We are excited to welcome Isabelle Siegrist to the Sciencepreneurship panel at the Workshop on Multimodal Foundation Models!🚀 Isabelle will bring an entrepreneurial perspective on turning research into real-world innovation. 🔗 Register for the online event on July 1: elliot-ai.eu/events/multi...

We're excited to welcome Ioannis Patras as a speaker at the Workshop on Multimodal Foundation Models! 🤖 Professor at Queen Mary University of London & Head of Research at Tavus Inc., he will present “Multimodal AI for Human Behaviour Analysis and Synthesis”. 🔗 elliot-ai.eu/events/multi... @ellis.eu

How do we scale audio AI without skyrocketing computing costs? 🎧 Shreya Sajid (@tue.nl) shares ELLIOT’s research on token compression, reducing tokens for sound, music & speech to build leaner, faster, and more sustainable multimodal AI. Explore our use cases: www.elliot-ai.eu/use-cases

We are excited to welcome @jai-bardhan.bsky.social as a speaker at our upcoming workshop! 🤖🌍 Researcher at CIIRC CTU, he will present “Robot World Models”, exploring how video-based models can support robotic planning, prediction and interaction with the physical world. Register via the comments 👇

Want to see how we bring safe, connected, and multimodal AI to life? 🚀 Explore our new Video Library! Your central hub for expert explainers, partner interviews, and major event highlights. 🎬 🔗 www.elliot-ai.eu/videos

We are excited to welcome Joost van de Weijer as a speaker at the Workshop on Multimodal Foundation Models! 🤖 He will present “Towards Accurate and Efficient Model Merging”, exploring how task-specific models can be combined into more efficient multi-task AI systems. 🔗 Link in the comments.

That's a wrap on the Summer School on Robotic Manipulation in Prague! 🤖 3 days of amazing deep dives & collaboration with AGIMUS, @erc.europa.eu FRONTIER & ELIAS. Huge thanks to all our brilliant speakers & attendees, in-person and online! 🚀

On 27 and 28 May, ELLIOT joined @ellis.eu, ELIAS & @elsa-ai.eu for the Human-centric ML Workshop 2026, hosted by @ellisalicante.org 🤝🚀 Through a hybrid exchange, we tackled the future of AI safety, fairness & transparency. A vital space for shared reflection! What an inspiring event! 🙌

Missed the deadline? You’re in luck! 🚨 👉 Deadline Extended: Friday, 12 June! Last call to dive into robust, multimodal AI for autonomous driving! 🏎️✨ 👇 Apply before Friday! pages.cvc.uab.es/ssadriving/ @ellis.eu @valeoai.bsky.social @uab.cat

ELLIOT Project@elliot-eu.bsky.social · 3mo ago

The future of Autonomous Driving is heading to Barcelona! 🏎️🏙️ Supported by ELLIOT, this ELLIS Summer School allows researchers to learn from experts and build new collaborations over four intensive days. 🚀 Apply by 8 June! ⏳ pages.cvc.uab.es/ssadriving/ @ellis.eu @valeoai.bsky.social @uab.cat