Aliki Anagnostopoulou

A case study for contextualised image captioning uning foundation models: journalism enhancement with AI

Large language models (LLMs) and large multimodal models (LMMs) have significantly impacted the AI community, industry, and various economic sectors. In journalism, integrating AI poses unique challenges and opportunities, particularly in enhancing the quality and efficiency of news reporting. This study explores how LLMs and LMMs can assist journalistic practice Read more

By Anika Heinen-Hilgemeyer, ago

Towards self-improving scene understanding with vision-language knowledge integration

Image captioning has seen immense progress in the last few years. However, general-purpose systems often fail to provide personalised, context-aware captions tailored to individual users or domains. In this work, we investigate the task of personalised and contextualised image captioning by leveraging foundational models, including large language models (LLMs) and Read more

By Anika Heinen-Hilgemeyer, ago

Two IML contributions at IJCAI 2024

Starting from its inception in 1969, the International Joint Conference on Artificial Intelligence (IJCAI) has been the premier venue for the global AI community to share and celebrate advancements in artificial intelligence research. This year’s edition took place in Jeju, South Korea (main conference acceptance rate 15%), and the Interactive Read more

By Franziska Scheurer, ago

Science Slam x AI Grid

On May 23rd, Aliki Anagnostopoulou from IML participated in a Science Slam event held at Hubraum Berlin, organized by the AI Grid — an initiative that provides networking, mentoring opportunities, and more to master’s and PhD students. The concept of the Science Slam is simple: each presenter has 10 minutes Read more

By Franziska Scheurer, ago