Peter Vickers

I am a Computer Scientist with specialisation in Natural Language Processing and Multimodal AI. Currently, I am in the final year of my Ph.D. at The University of Sheffield, where my research focuses on augmenting language models with multimodal information. My advisor is Nikos Aletras, and previously Loïc Barrault. My PhD is dual-funded by the UKRI Centre for Doctoral Training (CDT) in Speech and Language Technologies and an Amazon Studentship Grant.

My work is enhancing models’ capabilities through multimodal data for tasks including Visual Question Answering, Text-to-Image Retrieval, and Citation Recommendation. I am also interested in better metrics for these tasks.

During my PhD, I joined the JSALT summer workshop twice: Multi-lingual Speech to Speech Translation for Under-Resourced Languages in Johns Hopkins, Baltimore, USA (2022) and Better Together: Text + Context in Le Mans, France (2023). At Amazon UK I interned as an Applied Scientist where I adapted Vision-Language models for Text-Image Retrieval (2022-2023).

Before my Ph.D, I had an MSc in Computer Science with Speech and NLP from the University of Sheffield, and a BA in English Language and Literature from Magdalen College, Oxford.

In my free time I enjoy backcountry ski tours: the Hardangervidda and Jotunheimen areas of Norway are my favourite. In 2022 I took part in a two-week trip to the High Arctic in Trollheimen, Svalbard where I learned to build igloos. After submitting my thesis, I will lead the five week 2024 UK Stauning Alps expedition to Eastern Greenland.