Researchers present a model that recognises floating plastics in satellite images. This could help to systematically remove plastic litter from the oceans with ships.
We propose the asymmetric certified robustness problem, which requires certified robustness for only one class and reflects real-world adversarial scenarios.
In July, 2023, Science Gallery London and the London Office of Technology and Innovation co-hosted a workshop helping Londoners think about the kind of AI they want.
How can we reconcile the ease of specifying tasks through natural language-based approaches with the performance improvements of goal-conditioned learning?
Thoroughly testing video game software by hand is difficult. AI agents that can automatically explore different game functionalities are a promising alternative.
Legislation regulating AI safety and transparency is needed, say researchers, so British industry and education can put resources into AI development with confidence.