about | Ω research group

We (Ω) are a research group based at UCL Computer Science and the UCL Centre for Artificial Intelligence (AI). We conduct research within the domains of machine learning and natural language processing or, more plainly, AI. The group lead is Dr Vasileios Lampos.

Our work has shaped a significant part of the digital/computational epidemiology field (1, 2, 3, 4, 5), with models driven by online search information being incorporated to routine epidemiological systems in the UK for the first time (1, 2, 3). Another significant portion of our research aimed to develop models that can better understand socio-economic or socio-political trends through the lens of our society's most popular digital twin: social media (1, 2, 3, 4, 5, 6). And then we have also delivered machine learning, AI or NLP models that proposed important foundational insights in tasks related to autism/education, computational law, and computational sociology.

Our more recent research focuses on modelling sequential information. We have proposed state-of-the-art forecasting methods for multi-variable time series forecasting (1, 2, 3), and have studied the phenomenon of model collapse that can emerge during the training of large language models (LLMs).

If you would like to join us, please read this information and do not hesitate to reach out to find out more.

[ Why Ω? ]

Recent news (all)

Nov 08, 2025	Our paper “Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting” has been accepted by AAAI 2026 (main) for an oral presentation.
Nov 01, 2025	Fully-funded PhD studentship (4 years)
Sep 19, 2025	Our project “Foundation models for sequential predictions” has been awarded 10,000 GPUh on the Isambard AI AIRR service.
Aug 21, 2025	Our paper “Machine-generated text detection prevents language model collapse” has been accepted by EMNLP 2025 (main).
Apr 01, 2025	Our paper titled “DeformTime: capturing variable dependencies with deformable attention for time series forecasting” has been published in the Transactions on Machine Learning Research (TMLR).

Highlighted publications (all)

AAAI

Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting

Yuxuan Shu and Vasileios Lampos

In Proc. of the AAAI Conference on Artificial Intelligence, 2026

DOI Bib PDF Supp Video Code

@inproceedings{shu2026sonnet,
  title = {{Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting}},
  author = {Shu, Yuxuan and Lampos, Vasileios},
  booktitle = {Proc. of the AAAI Conference on Artificial Intelligence},
  volume = {40},
  number = {30},
  pages = {25419--25427},
  year = {2026},
  doi = {10.1609/aaai.v40i30.39736},
}

TMLR

DeformTime: capturing variable dependencies with deformable attention for time series forecasting

Yuxuan Shu and Vasileios Lampos

Transactions on Machine Learning Research, 2025

Bib PDF Code

@article{shu2025deformtime,
  title = {{DeformTime: capturing variable dependencies with deformable attention for time series forecasting}},
  author = {Shu, Yuxuan and Lampos, Vasileios},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2025},
  url = {https://openreview.net/forum?id=M62P7iOT7d},
}

EMNLP

Machine-generated text detection prevents language model collapse

George Drayson, Emine Yilmaz, and Vasileios Lampos

In Proc. of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

DOI Bib PDF Video Code

@inproceedings{Drayson2025,
  author = {Drayson, George and Yilmaz, Emine and Lampos, Vasileios},
  title = {{Machine-generated text detection prevents language model collapse}},
  booktitle = {Proc. of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  pages = {29645--29661},
  doi = {10.18653/v1/2025.emnlp-main.1506},
}

npj Digit Med

Tracking COVID-19 using online search

Vasileios Lampos, Maimuna S. Majumder, Elad Yom-Tov, Michael Edelstein, Simon Moura, Yohhei Hamada, Molebogeng X. Rangaka, Rachel A. McKendry, and Ingemar J. Cox

npj Digital Medicine, 2021

DOI Bib PDF

@article{Lampos2021covid,
  title = {{Tracking COVID-19 using online search}},
  author = {Lampos, Vasileios and Majumder, Maimuna S. and Yom-Tov, Elad and Edelstein, Michael and Moura, Simon and Hamada, Yohhei and Rangaka, Molebogeng X. and McKendry, Rachel A. and Cox, Ingemar J.},
  journal = {npj Digital Medicine},
  year = {2021},
  doi = {10.1038/s41746-021-00384-w},
  volume = {4},
  number = {17},
}

Sci Rep

Advances in nowcasting influenza-like illness rates using search query logs

Vasileios Lampos, Andrew C. Miller, Steve Crossan, and Christian Stefansen

Scientific Reports, 2015

DOI Bib PDF

@article{Lampos2015GFT,
  author = {Lampos, Vasileios and Miller, Andrew C. and Crossan, Steve and Stefansen, Christian},
  title = {{Advances in nowcasting influenza-like illness rates using search query logs}},
  journal = {Scientific Reports},
  year = {2015},
  doi = {10.1038/srep12760},
  volume = {5},
  number = {12760},
}

WWW

Enhancing feature selection using word embeddings: The case of flu surveillance

Vasileios Lampos, Bin Zou, and Ingemar J. Cox

In Proc. of the 26th International World Wide Web Conference, 2017

DOI Bib PDF

@inproceedings{Lampos2017,
  author = {Lampos, Vasileios and Zou, Bin and Cox, Ingemar J.},
  title = {{Enhancing feature selection using word embeddings: The case of flu surveillance}},
  booktitle = {Proc. of the 26th International World Wide Web Conference},
  pages = {695--704},
  year = {2017},
  doi = {10.1145/3038912.3052622},
}

Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspective

Nikolaos Aletras, Dimitrios Tsarapatsanis, Daniel Preoţiuc-Pietro, and Vasileios Lampos

PeerJ Computer Science, 2016

DOI Bib PDF

@article{Aletras2016ECtHR,
  author = {Aletras, Nikolaos and Tsarapatsanis, Dimitrios and Preo\c{t}iuc-Pietro, Daniel and Lampos, Vasileios},
  title = {{Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspective}},
  journal = {PeerJ Computer Science},
  year = {2016},
  doi = {10.7717/peerj-cs.93},
  volume = {2},
  pages = {e93},
}

An artificial intelligence approach for selecting effective teacher communication strategies in autism education

Vasileios Lampos, Joseph Mintz, and Xiao Qu

npj Science of Learning, 2021

DOI Bib PDF

@article{Lampos2021autism,
  title = {{An artificial intelligence approach for selecting effective teacher communication strategies in autism education}},
  author = {Lampos, Vasileios and Mintz, Joseph and Qu, Xiao},
  journal = {npj Science of Learning},
  year = {2021},
  doi = {10.1038/s41539-021-00102-x},
  volume = {6},
  number = {25},
}