Foundation models like CLIP are trained on hundreds of millions of samples and effortlessly
generalize to new tasks and inputs. Out of the box, CLIP shows stellar zero-shot and few …

Purpose Following the recent rise in generative artificial intelligence (GenAI) tools,
fundamental questions about their wider impacts have started to reverberate around various …

Out-of-Domain (OOD) generalization is the ability of a model trained on one or more
domains to generalize to unseen domains. In the ImageNet era of computer vision …

Growing amount and quality of AI-generated texts makes detecting such content more
difficult. In most real-world scenarios, the domain (style and topic) of generated data and the …

Computational fact-checking (FC) relies on supervised models to verify claims based on
given evidence, requiring a resource-intensive process to annotate large volumes of training …

Chatbots built upon language models have exploded in popularity, but they have largely
been limited to synchronous, turn-by-turn dialogues. In this paper we present a simple yet …

With the emergence of Artificial Intelligence (AI), our lives and economy are under-going a
profound transformation. While there are huge benefits to be realized by the technology, we …

Language model alignment has become an important component of AI safety, allowing safe
interactions between humans and language models, by enhancing desired behaviors and …

Denne avhandlingen utforsker krysningen mellom dype generative modeller og
forsterkningslæring, med søkelys på tilpasningen av diffusjonsbaserte tekst-til-bilde …