Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

European Large Open Multi-Modal Foundation Models For Robust Generalization On Arbitrary Data Streams

Project description

Developing open multimodal foundation models for real-world, data-rich applications

Leveraging Europe’s AI talent and supercomputing infrastructure, the EU-funded ELLIOT project will develop a family of open trustworthy Multimodal Generalist Foundation Models: AI systems designed to learn general knowledge and patterns from massive amounts of data of various types – from videos, images and text to sensor signals, industrial time series and satellite feeds – and efficiently transfer the knowledge gained to different downstream tasks. Unlike current foundation models, which face significant challenges in terms of generalisation and support for multimodal data, ELLIOT’s models will be capable of robust generalisation and reasoning across conditions not seen during training, coping well with dynamic, noisy, temporally-evolving multimodal data streams. This will empower new applications for media, earth modelling, robots, mobility, computer engineering and workflow automation.

Objective

At the heart of ELLIOT is the development of open Multimodal Generalist Foundation Models (MGFMs): AI systems designed to learn general knowledge and patterns from massive amounts of data of various types — from videos, images, and text to sensor signals, industrial time series, and satellite feeds — and efficiently transfer the generic knowledge learned in generalist manner to a wide variety of downstream tasks. Unlike current foundation models that face significant challenges in terms of generalisation capabilities and support for multimodal data, ELLIOT’s models will be capable of robust generalisation across conditions not seen during the training, coping well with dynamic, noisy, and temporally-evolving multimodal data streams. Real and synthetic data, to mitigate data scarcity, will be leveraged for training MGFMs and for further adapting them for specific downstream tasks in domains like media, earth observation, robot perception, mobility, computer engineering and workflow automation. Real data used for training will include data directly provided by members of the consortium as well as data from relevant European Data Spaces, while complementary synthetic data will be generated by exploiting existing generative AI capabilities as well as new ones developed in the project. European HPC infrastructure is directly included in the consortium to ensure the availability of the necessary computing resources.

Fields of science (EuroSciVoc)

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-RIA - HORIZON Research and Innovation Actions

See all projects funded under this funding scheme

Call for proposal

(opens in new window) HORIZON-CL4-2024-HUMAN-03

See all projects funded under this call

Coordinator

ETHNIKO KENTRO EREVNAS KAI TECHNOLOGIKIS ANAPTYXIS
Net EU contribution
€ 3 077 920,05
Address
CHARILAOU THERMI ROAD 6 KM
570 01 THERMI THESSALONIKI
Greece
Region
Βόρεια Ελλάδα Κεντρική Μακεδονία Θεσσαλονίκη
Activity type
Research Organisations
Links
Total cost
€ 3 077 920,05

Participants (34)

Partners (2)