2 papers
cs.CL2024
Towards Safe Multilingual Frontier AI
Artūrs Kanepajs, Vladimir Ivanov, Richard Moulange
Linguistically inclusive LLMs -- which maintain good performance regardless of the language with which they are prompted -- are necessary for the diffusion of AI benefits around th…
cs.CV2024
Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
Andrei Semenov, Vladimir Ivanov, Aleksandr Beznosikov +1
We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs). While SOTA approaches to Image Classification task work as a black b…