Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Germany

European Research Council grant · Running

MIDAS Modeling the Integrated minD At Scale

Coordinator
Max-Planck-Gesellschaft Zur Forderung Der Wissenschaften eV, Germany
Runs
1 January 2027 to 31 December 2031
Status
Running
EU funding
€1.5m
Total cost
€1.5m
Partners
1 organisations in 1 countries
Type
European Research Council grant
Grant agreement
101302651

What the project is doing

In the project's own words, from its summary on CORDIS.

At the heart of cognitive science lies a fundamental question: how does the human mind transform incoming information into behavior? Computational cognitive models translate psychological theories into algorithmic form, making it possible to uncover cognitive processes that are not directly observable in behavior alone. Yet, despite their vast potential for advancing our understanding of the human mind, current cognitive models remain largely limited to narrow tasks or domains.

This fragmentation has contributed to psychology's broader generalization crisis and hindered theoretical integration. Modeling the Integrated minD At Scale (MIDAS) tackles this challenge by establishing a fundamentally new modeling paradigm – one centered around large-scale, integrated models capable of simulating, predicting, and explaining human behavior across a wide range of experimental paradigms. In doing so, MIDAS marks a transformative step for cognitive modeling, shifting the field from fragmented, task-specific approaches toward a unified theory that reflects the full richness of human cognition.

MIDAS is structured around three key objectives. First, to develop cognitive models capable of capturing human behavior in any experiment expressible in natural language. Second, to establish a robust methodological framework for evaluating and comparing large-scale, integrated models. Third, to extend such models to more naturalistic environments. To achieve these objectives, MIDAS draws on cutting-edge methods across cognitive science, machine learning, and language modeling, applied to behavioral data at unprecedented scale.

My prior work has laid the foundations for this approach, notably through my leadership of an international collaboration that produced one of the first large-scale datasets for integrative cognitive modeling. With the methodological tools and infrastructure now mature enough, the field is ready for a transformation – and I am uniquely positioned to spearhead it.

Who is involved

OrganisationCityCountryRole
Max-Planck-Gesellschaft Zur Forderung Der Wissenschaften eVMunchenGermanyCoordinator

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS