Ilias Stogiannidis | The University of Edinburgh

About Me

My names is Ilias (pronounced as “ee-lee-ahs” or “ee-ly-ahs”) and I am a PhD Student in Engineering at The University of Edinburgh as a member of the Vios Science Lab under the supervision of Prof. Sotirios Tsaftaris. My research focuses on Foundational Computer Vision Models and Applications. I am particularly interested in the intersection of Computer Vision and Natural Language Processing, and how we can leverage multimodal data to build more robust and interpretable models. I am also interested in Reinforcement Learning and how we can use it to train agents to perform complex tasks in the real world.

Prior to my PhD, I completed my MSc in Computer Science at Athens University of Economics and Business (AUEB) under the supervision of Prof. Ion Androutsopoulos. I also worked as an Applied Machine Learning Researcher at helvia.ai, specializing in NLP and Large Language Models. I am an active member of the Natural Language Processing Group at AUEB where we conduct research on NLP and Machine Learning.

Feel free to reach out to me if you are interested in collaborating or if you have any questions about my research! Currently, the time for me is:

Research Interests

My research interests vary from Natural Language Processing to Computer Vision and Deep Learning. I am particularly interested in the following topics:

Computer Vision: Object Detection & Tracking, Video Object Segmentation, Video Captioning
Natural Language Processing: Large Language Models, Text Generation, Alignment with Human Preference
Deep (Reinforcement) Learning: Multimodal Learning, Generative Adversarial Networks, Graph Neural Networks
Robot Learning: Human-Robot Interaction, Robot Navigation, Robot Vision

News

[Aug. 2024] I have parted ways with helvia.ai and I am now a PhD Student at The University of Edinburgh.
[Dec. 2023] My thesis is now available in the NLP Group’s website.
[Nov. 2023] Our paper has been selected for poster presentation at EMNLP 2023. See you in Singapore!
[Oct. 2023] My thesis in under the final review and will be available soon in the NLP Group’s website.
[Oct. 2023] Our paper about LLM caching is accepted to the Findings of EMNLP 2023.

Publications

EMNLP2023

Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models

Ilias Stogiannidis, Stavros Vassos, Prodromos Malakasiotis, Ion Androutsopoulos

In Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

PDF Code Project Page BibTex Poster Presentation

ICAIF2023

Making LLMs Worth Every Penny: Resource-Limited Text Classification in Finance

Lefteris Loukas, Ilias Stogiannidis, Odysseas Diamantopoulos-Pantaleon, Stavros Vassos, Prodromos Malakasiotis

In Proceedings of the 4th ACM International Conference on AI in Finance (ICAIF),New York, NY, USA, 2023.

PDF Project Page BibTex Oral Pressentation

FINNLP2023

Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance

Lefteris Loukas, Ilias Stogiannidis, Stavros Vassos, Prodromos Malakasiotis

In Proceedings of the Fifth Workshop on Financial Technology and Natural Language Processing and the Second Multimodal AI For Financial Forecasting of the International Joint Conference on Artificial Intelligence (IJCAI), Macao, China, 2023.

PDF BibTex Oral Pressentation

–>