The evaluation of machine-generated image captions poses an interesting yet persistent
challenge. Effective evaluation measures must consider numerous dimensions of similarity …

Generative artificial intelligence has made significant strides, producing text
indistinguishable from human prose and remarkably photorealistic images. Automatically …

If you ask a human to describe an image, they might do so in a thousand different ways.
Traditionally, image captioning models are trained to generate a single" best"(most like a …

Scaling up weakly-supervised datasets has shown to be highly effective in the image-text
domain and has contributed to most of the recent state-of-the-art computer vision and …

Direct Preference Optimization (DPO) has recently emerged as a popular approach to
improve reinforcement learning with human feedback (RLHF), leading to better techniques …

This dissertation is a collection of three independent but thematically connected papers on
language models. The first assesses a currently popular account of the nature of the …

If you ask a human to describe an image, they might do so in a thousand different ways.
Each of these descriptions depends not only on the image but also on a rich tapestry of …