An open multimodal Scientific Foundation Model (SciFM) unifying text, structures, images and simulation data to accelerate materials discovery across Europe.
SimuLingua delivers an open, multimodal Scientific Foundation Model (SciFM) for materials that unifies text, structures, images and simulation data to accelerate discovery across design–simulate–validate loops. Paired with a physics-in-the-loop generative engine and an AI-accelerated multi-scale simulation pipeline (DFT → phase-field → CFD/FEM), it creates a closed discovery loop: the model proposes promising candidates, fast surrogates verify plausibility and performance, and new data continuously flows back through a FAIR knowledge graph. A natural language interface lets domain experts query the KG, launch virtual experiments and steer multi-objective inverse design.
June 15–16, 2026 • CDMA Building, European Commission, Brussels
The SimuLingua consortium gathered in Brussels on 15-16 June 2026 for the project's joint kick-off event, hosted by the European Commission alongside the other newly funded projects in its cluster.
Funded under Horizon Europe (HORIZON-CL4-INDUSTRY-2025-01-DIGITAL-61) as a Research and Innovation Action, SimuLingua — Simulation-Powered Computational Linguistics for Materials Foundation Models — will build an open, multimodal Scientific Foundation Model (SciFM) for materials. The model unifies text, structures, images and simulation data to accelerate discovery across design–simulate–validate loops.
At its heart is a closed loop: the model proposes candidate materials, fast AI surrogates and a multiscale simulation pipeline (DFT → phase-field → CFD/FEM) verify their plausibility and performance, and new data flows back through a FAIR knowledge graph that provides ontologies, provenance and leakage-safe data splits. A natural-language interface lets domain experts query the knowledge graph, launch virtual experiments and steer generative inverse design.
Over 48 months, SimuLingua will advance from TRL 1 to TRL 4 and validate its approach across six use cases — including lead-free electroceramics, durable glasses, high-entropy and recyclable alloys, analyte-sensitive coatings, and a device-level olfactory sensing array. As a contribution to the GenAI4EU agenda, the project aims to deliver a sovereign, reusable blueprint for physics-grounded scientific AI, with all non-restricted models, datasets and code released openly with model and data cards, DOIs and APIs.
The Brussels kick-off brought together SimuLingua's nine partners from across Europe to align on objectives and the road ahead. Coordinated by Flowphys AS (Norway), the consortium includes KTH Royal Institute of Technology, the University of Sheffield, Eindhoven University of Technology, DYCOTEC Materials, OLIVERIS Tech Incubator, Vytautas Magnus University, the NGO Agency of Euro, and Thermo Challenges.
FLOWPHYS AS
(Coordinator, Norway)
KTH Royal Institute of Technology
Sweden
University of Sheffield
UK
TU Eindhoven
Netherlands
Dycotec Materials Ltd
UK
Oliveris Tech Incubator
Ireland
Vytautas Magnus University
Lithuania
Agency of European Innovations
Ukraine
Thermo Challenges Limited
UK
9 partners • 7 countries • Across Europe
Our full project website and communication channels will launch in August 2026 (M3), serving as the central hub for news, results and resources throughout SimuLingua's lifetime. Stay tuned!