@elliot-eu.bsky.social
๐ช๐บ ELLIOT is a Horizon Europe project developing the next generation of open and trustworthy Multimodal Generalist Foundation Models โ advancing open, general-purpose AI rooted in European values. ๐ค๐
@elliot-eu.bsky.socialHow can multimodal foundation models become more accessible across data types? ๐
On 8 Dec, ELLIOT and DVPS researchers will host โMultimodality for Everyone (M4E)โ in Paris ๐ซ๐ท, exploring low-resource modalities, efficient adaptation and more reusable multimodal AI.
@elliot-eu.bsky.socialHow can multimodal foundation models become more accessible across data types? ๐
On 8 Dec, ELLIOT and DVPS researchers will host โMultimodality for Everyone (M4E)โ in Paris ๐ซ๐ท, exploring low-resource modalities, efficient adaptation and more reusable multimodal AI.
@elliot-eu.bsky.social๐ Hello from Stuttgart! ๐ฉ๐ช ELLIOT was at the Frontier AI Innovation Summit, bringing a perspective on the future of AI in Europe to a community of researchers and innovators. We also hosted a workshop on training frontier AI models, a great opportunity to exchange ideas and share ELLIOTโs insights ๐ค
@elliot-eu.bsky.social๐ Explore the paper: openaccess.thecvf.com/content/ICCV...
@elliot-eu.bsky.socialAI models can learn hidden visual biases from data. ๐ง โ๏ธ In this ELLIOT Research Spotlight ๐ฌ, we highlight MAVias from CERTH-ITI โ an approach using foundation models to discover and mitigate unknown visual biases, supporting more trustworthy computer vision systems. ๐ Paper in comments ๐
@elliot-eu.bsky.socialWhat does a day in the life of an AI researcher look like? ๐ป
In this ELLIOT testimonial, Aditya Gulati from @ellisalicante.org shares a glimpse into his daily work, from coding and reading papers to meetings, collaboration and continuous learning.
Watch his testimonial ๐ youtu.be/Vcke5SfSsfY
@elliot-eu.bsky.social๐ On 26 Nov, ELLIOT joins ELIAS in Milan for the Theme Development Workshop on AI for a Sustainable Society.
The event will explore AIโs role in societal & environmental challenges, emerging research directions and new collaborations.
@elliot-eu.bsky.socialHow can autonomous driving AI become more efficient? ๐
๐ฌWe highlight DrivoR by @valeoai.bsky.social, a transformer-based approach that compresses multi-camera information into compact scene representations while supporting safer, more adaptive driving decisions.
Read it๐ arxiv.org/pdf/2601.05083
@elliot-eu.bsky.socialELLIOT in Ljubljana! ๐ธ๐ฎ Cees Snoek delivered the keynote at the inaugural ELLIS Unit Slovenia event, taking the audience from 500M years of vision and language to ELLIOTโs multimodal AI and his latest work on multilingual image generation. ๐ง Thanks to the ELLIS Unit Slovenia for the invitation! ๐
@elliot-eu.bsky.social๐ง What should AI remember โ and what should it forget? At NeurIPS 2026, ELLIOT is supporting PALM, a workshop on personalised, aligned and long-term AI memory, organised by researchers including our CISPA partners. ๐ 13 Dec ๐ Paris ๐ซ๐ท
@elliot-eu.bsky.social๐ Read the full paper: arxiv.org/abs/2511.07236
@elliot-eu.bsky.socialCan a tabular foundation model help uncover what causes what? ๐ In this ELLIOT Research Spotlight ๐ฌ, we highlight โDoes TabPFN Understand Causal Structures?โ, a paper from the University of Freiburg and Prior Labs on causal information in TabPFN embeddings. โ Info in the comments.
@elliot-eu.bsky.socialAI can help write code, but it can also reproduce hidden bugs and security risks ๐งโ๐ป๐
In this use case video, Christoph Landolt (CISPA) and Xuecong โSabrinaโ Liu (OPENCHIP) discuss their work on safer AI-generated code and multimodal support for hardware design.
Full video ๐ youtu.be/UUANvrIDGTs
@elliot-eu.bsky.socialTo celebrate European Researchers' Night, our infographic is taking centre stage on the European Corner webpage!
Check out our new infographic featured in the European Corner to see how ELLIOT blends text, video & sensor data for real-world impact!๐
Explore it ๐
cms.elliot-ai.eu/assets/promo...
@elliot-eu.bsky.socialTrustworthy AI isn't just a slogan for ELLIOT, it's a core workstream! ๐ง ๐ก๏ธ
From EU AI Act compliance and bias mitigation to data privacy, explainability, and security, we're building safe European AI by design.
Learn more ๐
www.elliot-ai.eu
@elliot-eu.bsky.socialWhat if video AI could move between different types of information?
๐ฅ In the final Poster Session video, Muhammad Khattak (EPFL) presents an any-to-any video model designed to take different video-related inputs and predict other modalities across space and time.
Watch it ๐ youtu.be/mj7eJrHAInw
@elliot-eu.bsky.socialWe were in Barcelona for the Summer School on Autonomous Driving! ๐ The event explored how AI can support safer, smarter mobility in complex real-world environments. It was great to see so much curiosity, technical exchange and energy in Barcelona. ๐ค
@elliot-eu.bsky.social๐ช๐บ How can Europe strengthen frontier AI?
On 8 Oct, ELLIOT will host โTraining Frontier AI Models in Europeโ at the German AI Centers & ELIAS Alliance event, , exploring trustworthy foundation models.
๐ Messe Stuttgart, Germany
๐
8 October 2026
๐ More details: elliot-ai.eu/events/all-h...
@elliot-eu.bsky.social๐ Read the full paper: arxiv.org/abs/2411.02470
@elliot-eu.bsky.socialWhen AI explains a decision, is the explanation useful to people โ or only to the model? ๐ In this ELLIOT Research Spotlight ๐ฌ, we highlight PASTA, a human-aligned benchmark for evaluating XAI explanations in computer vision from University of Trento and other partners. Paper in comments ๐
