Ilias Stogiannidis profile picture

Ilias Stogiannidis

PhD Student
The University of Edinburgh


About Me

My name is Ilias (pronounced “ee-lee-ahs” or “ee-ly-ahs”), and I’m a PhD student at The University of Edinburgh. I’m part of the Vios Science Lab under the guidance of Prof. Sotos Tsaftaris and Dr. Steven McDonagh.

My research interests lie in spatial and temporal reasoning in Foundational Models. I’m also interested in multimodal learning and efficient models. Additionally, I’m fascinated by the intersection of Computer Vision and Natural Language Processing and Robotics.

Before embarking on my PhD, I completed my MSc in Computer Science at Athens University of Economics and Business (AUEB). I was supervised by Prof. Ion Androutsopoulos. Furthermore, I had the opportunity to work as an Applied Machine Learning Researcher at helvia.ai, specializing in Natural Language Processing and Large Language Models.

I’m also an active member of the NLP Group at AUEB, where we conduct research in 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

🧠

Foundation & Reasoning

  • Spatial / Temporal Reasoning
  • Multimodal Alignment
  • Efficient Fine-Tuning
👁️

Computer Vision

  • Spatio-Semantic Modeling
  • Generative / Diffusion Models
  • Graph & Structured Perception
💬

NLP & LLMs

  • Instruction Following
  • Reasoning & Tool Use
  • Retrieval & Memory
🤖

Robotics & RL

  • Embodied Agents
  • Multi-Agent Interaction
  • Socratic / Human-in-the-loop

News

Dec. 2024
Visiting AUEB (20th) to give a talk about pursuing a PhD abroad.
Aug. 2024
Started PhD at The University of Edinburgh.
Dec. 2023
MSc thesis available on NLP Group website.
Nov. 2023
Poster presentation at EMNLP 2023 (Singapore).
Oct. 2023
Thesis under final review.
Oct. 2023
LLM caching paper accepted to Findings of EMNLP 2023.

Publications

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

  2. Making LLMs Worth Every Penny: Resource-Limited Text Classification in Finance thumbnail 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 Presentation

  3. Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance thumbnail 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 Presentation

–>


Powered by Jekyll and Minimal Light theme.