Gerasimos (Makis) Lampouras

Most people call me Makis (he/him).

prof_pic_gl.jpg

Hello there! :smirk_cat:

I am a Principal Research Scientist and currently serve as the Team Leader of the Speech and Language group in Huawei Noah’s Ark Lab, London. If you are intersted in joining us, you can find information about open positions here. Also, keep in mind that spots for Research Internships are open all year round and you can apply through here.

My areas of interest generally fall somewhere between Natural Language Processing and Machine Learning, with my latest efforts focused on improving the auto-regressive reasoning capabilities of Large Language Models. Recently this journey has led me to try and teach LLMs to generate / understand programming languages, while previously my work was more focused on natural language generation, dialogue systems, and machine learning applications for NLP.

Previously, I was a research associate at the University of Cambridge, University of Sheffield and University College London. I graduated and received my MSc and PhD from the Athens University of Economics and Business.

In my spare time, I survive my cat and struggle to keep up with too many intestests, but I do enjoy reading fiction, playing games (board, video, and dungeon mastering TTRPGs), and (unfortunately rarely) paint.

selected publications

  1. arXiv
    SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
    Fenia Christopoulou ,  Ronald Cardenas ,  Gerasimos Lampouras , and 2 more authors
    arXiv pre-print, 2024
  2. arXiv
    Human-like Episodic Memory for Infinite Context LLMs
    Zafeirios Fountas ,  Martin A Benfeghoul ,  Adnan Oomerjee , and 4 more authors
    arXiv pre-print, 2024
  3. EACL
    Text-to-Code Generation with Modality-relative Pre-training
    Fenia Christopoulou ,  Guchun Zhang ,  and  Gerasimos Lampouras
    In Proceedings of the European Chapter of the Association for Computational Linguistics (EACL), 2024
  4. arXiv
    PanGu-Coder: Program synthesis with function-level language modeling
    Fenia Christopoulou ,  Gerasimos Lampouras ,  Milan Gritta , and 8 more authors
    arXiv pre-print, 2022
  5. EMNLP
    Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis
    Philip John Gorinski ,  Matthieu Zimmer ,  Gerasimos Lampouras , and 2 more authors
    In Findings of the Association for Computational Linguistics - EMNLP, 2023