Biography
Oiwi leads the Neural Processing Lab (PNPL) at the University of Oxford. His aim is to build bridges between deep learning and the brain, for example by accelerating the development of Brain Computer Interfaces (BCIs), but also by developing deep learning methods for interpreting brain data and leveraging principles of systems neuroscience to inform machine learning. Oiwi completed a DPhil focused on Natural Language Processing (NLP) for low-resource languages. He further trained as a postdoc in Imaging Neuroscience at UCL and Oxford, and in Applied Artificial Intelligence at the ORI. He was previously a lecturer in Medicine at St Peter's College, Oxford, and is currently Hugh Price Fellow in Computer Science at Jesus College, Oxford.
Recent Publications
The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100
Mantegna F, Elvers G, Jayalath D, Landau G, Kim T et al. (2026)
BibTeX
@misc{thepnplcompetit-2026/9,
title={The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100},
author={Mantegna F, Elvers G, Jayalath D, Landau G, Kim T et al.},
year = "2026"
}
A Common Measure of Communication for Speech Brain-Computer Interfaces
Jayalath D, Ballyk B & Jones OP (2026)
BibTeX
@misc{acommonmeasureo-2026/9,
title={A Common Measure of Communication for Speech Brain-Computer Interfaces},
author={Jayalath D, Ballyk B & Jones OP},
year = "2026"
}
LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale
Mantegna F, Jayalath D, Elvers G, Kim T, Ballyk B et al. (2026)
BibTeX
@misc{libribrainonehu-2026/8,
title={LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale},
author={Mantegna F, Jayalath D, Elvers G, Kim T, Ballyk B et al.},
year = "2026"
}
Acoustic properties of utterance-initial glottal stop in Hawaiian
Roon KD, Davidson L & Parker Jones O (2026), Journal of the Acoustical Society of America, 159(5), 4038-4055
BibTeX
@article{acousticpropert-2026/5,
title={Acoustic properties of utterance-initial glottal stop in Hawaiian},
author={Roon KD, Davidson L & Parker Jones O},
journal={Journal of the Acoustical Society of America},
volume={159},
pages={4038-4055},
publisher={Acoustical Society of America},
year = "2026"
}
Modelling Discrete States and Long-Term Dynamics in Functional Brain Networks
Cho S, Huang R, Gohil C, Jones OP & Woolrich MW (2026), Imaging Neuroscience
BibTeX
@article{modellingdiscre-2026/4,
title={Modelling Discrete States and Long-Term Dynamics in Functional Brain Networks},
author={Cho S, Huang R, Gohil C, Jones OP & Woolrich MW},
journal={Imaging Neuroscience},
publisher={MIT Press},
year = "2026"
}
MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
Jayalath D & Jones OP (2026)
BibTeX
@misc{megxldataeffici-2026/2,
title={MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training},
author={Jayalath D & Jones OP},
year = "2026"
}
MEGnifying Emotion: Sentiment Analysis from Annotated Brain Data
Liu B & Jones OP (2026)
BibTeX
@misc{megnifyingemoti-2026/1,
title={MEGnifying Emotion: Sentiment Analysis from Annotated Brain Data},
author={Liu B & Jones OP},
year = "2026"
}
Separating the forest from the palm trees: Individual variation in a presurgical language mapping task
Voets NL, Parker Jones O, Seghier ML & Plaha P (2026), NeuroImage Clinical, 49, 103943
BibTeX
@article{separatingthefo-2026/,
title={Separating the forest from the palm trees: Individual variation in a presurgical language mapping task},
author={Voets NL, Parker Jones O, Seghier ML & Plaha P},
journal={NeuroImage Clinical},
volume={49},
pages={103943},
publisher={Elsevier},
year = "2026"
}
MEG-GPT: a transformer-based foundation model for magnetoencephalography data
Huang R, Cho S, Gohil C, Parker Jones O & Woolrich M (2025)
BibTeX
@misc{meggptatransfor-2025/10,
title={MEG-GPT: a transformer-based foundation model for magnetoencephalography data},
author={Huang R, Cho S, Gohil C, Parker Jones O & Woolrich M},
year = "2025"
}
LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale
Özdogan M, Landau G, Elvers G, Jayalath D, Somaiya P et al. (2025)
BibTeX
@misc{libribrainoverh-2025/6,
title={LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale},
author={Özdogan M, Landau G, Elvers G, Jayalath D, Somaiya P et al.},
year = "2025"
}
