ARIA TA1.1: Learning-Theoretic AI Safety
Failed source checkDate
Jun 2024
Data source
Source
Notes
[Safeguarded AI TA1.1] Learning-Theoretic AI Safety. Lead(s): Vanessa Kosoy, David Manheim, Alexander Appel, Gergely Szucs. Institutions: ALTER. Status: closed.
Other Grants by Advanced Research and Invention Agency (ARIA)
87| Grant | Recipient | Amount | Date |
|---|---|---|---|
| ARIA TA1.4: Field Building for Better Formal Models of Society | Meaning Alignment Institute | Feb 2025 | |
| ARIA TA1.3: Safeguarded Collaboration with AI Agents in a Type-Theoretic Computational Environment | University of Michigan | Sep 2024 | |
| ARIA TA1.1: Hyper-optimised Tensor Contraction for Neural Networks Verification | University of Birmingham | Jun 2024 | |
| ARIA TA1.1: Monoidal Coalgebraic Metrics | University Of Pisa | Jun 2024 | |
| ARIA TA1.2: CatColab: Collaborative modeling, specification, and verification | Topos Institute | Sep 2024 | |
| ARIA TA3: Digital Custodians for Ageing Infrastructure | Mind Foundry / WSP | Sep 2024 | |
| ARIA TA1.1: ULTIMATE: Universal Stochastic Modelling, Verification and Synthesis Framework | University Of York | Jun 2024 | |
| ARIA TA3: Safeguarded AI-Enabled Biopharmaceutical Manufacturing | University of Birmingham | Sep 2024 | |
| ARIA TA3: SAILS: Safeguarded AI for Logistics and Supply chain | HASH | Sep 2024 | |
| ARIA TA1.1: Modal Types for Quantitative Analysis | University Of Kent | Jun 2024 |
Showing 10 of 87 grants