On June 29–30, 2026, the partners of the Horizon Europe project ELLIOT – European Large Open Multi-Modal Foundation Models for Robust Generalization on Arbitrary Data Streams met in Barcelona for the project’s 4th plenary meeting, hosted by the Computer Vision Center (CVC-CERCA), the ELLIS Unit Barcelona and the Barcelona Supercomputing Center (BSC). The Modena ELLIS Unit took part with a team from AImageLab, presenting the progress of Work Package 2, which is led by UNIMORE and focuses on the training of open multimodal foundation models.
Over two days, the consortium reviewed the status of all work packages and use cases, discussed the plans for the coming months and the preparation of the project’s first review, and visited the premises of BSC and CVC.
The plenary was followed, on July 1, by the public workshop “Multimodal Foundation Models: From Research to Innovation”, held at the Institut d’Estudis Catalans and co-organised by ELLIOT, the ELLIS Unit Barcelona, the ELLIS Programme on Multimodal Learning Systems, ELIAS and XARXA RDI-IA. The workshop reached full capacity with nearly 150 participants on site and around 100 online, with invited talks by Ioannis Patras, Dima Damen, Joost van de Weijer, Jai Bardhan and Vittorio Murino and a panel on turning frontier research into real-world multimodal AI.
👉 Read the ELLIOT news about the workshop
👉 Watch the recording
