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

Atlas / Israel

European Research Council grant · Running

GDLNeuralArt Geometric Deep Learning for Neural Artifacts: Symmetry-Aware Learning across Trained Model Weights, Internal Representations, and Gradients

Coordinator
Technion - Israel Institute of Technology, Israel
Runs
1 November 2026 to 31 October 2031
Status
Running
EU funding
€1.6m
Total cost
€1.6m
Partners
1 organisations in 1 countries
Type
European Research Council grant
Grant agreement
101300078

What the project is doing

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

The explosive growth of deep learning has created fundamentally new data modalities: the mathematical byproducts of neural network development. Practitioners generate daily vast amounts of valuable but underutilized data---trained model weights, internal representations from inference, and network gradients from training. These byproducts, which we term Neural Artifacts, contain crucial information about model behavior, optimization, and internal processing.

Learning on neural artifacts holds transformative potential. Learning on Weight Spaces - weights of trained models - could revolutionize model selection, editing and generation. Learning on internal representations enables efficient hallucination detection on Large Language Models and other analyses. Learning on gradient spaces could transform model optimization and analysis. However, existing methods for learning on neural artifacts achieve only a fraction of this potential as they fail to account for fundamental mathematical structure, leaving the field without principled methods to harness the full power of these emerging data types.

The key insight is that neural artifacts share deep mathematical structures—symmetries inherited from their underlying architecture. By developing a geometric deep learning framework that respects these symmetries, we can unlock their full potential. Building on our pioneering equivariant architectures for neural artifacts, we propose developing theoretical foundations and practical tools. This includes designing symmetry-aware architectures, establishing theoretical guarantees, developing novel applications, and delivering open-source implementations.

Success will provide practitioners with powerful tools for understanding, generating, optimizing, and controlling neural artifacts. This research transforms neural computation byproducts into learnable information— extremely challenging due to their high dimensionality and symmetry structure, but with revolutionary potential.

Topics

Who is involved

OrganisationCityCountryRole
Technion - Israel Institute of TechnologyHaifaIsraelCoordinator

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