Imperial College London spinout Cogitat has been acquired by the neurotech company Indivi for an undisclosed sum. Indivi, based in Basel, Switzerland, plans to use the technology to help pharmaceutical companies detect whether experimental treatments for neurodegenerative diseases such as Alzheimer’s are impacting underlying biology.
Cogitat, launched in December 2020, developed a brain-computer interface allowing users to control virtual reality games using the mind. Its early deep learning models recognised behavioural intentions from electroencephalogram (EEG) headsets, later extending to interpret users’ attention or distraction levels. The company's foundation model, NeuroRVQ, aims to be a general-purpose model for the brain, akin to large language models for language.
The acquisition will see Cogitat, which is based in the UK and Greece, function as a business unit at Indivi. This move is intended to drive the biotech's transformation into a neuroscience-based AI company with applications across life sciences and eventually consumer technology.
Cogitat's technology, which won first place in the EEG Transfer Learning (BEETL) competition at the NeurIPS conference, is attributed to the quality of training data acquired through carefully designed experiments at Imperial. Dr Dimitrios Adamos, Cogitat’s Chief Technology Officer and co-founder, highlighted the importance of designing experiments with a purpose, stating, “A cardiologist learns most from how the heart responds to exercise. We do the same with the brain: we record it while it’s at work.”
Dr Allan Ponniah, Cogitat CEO and co-founder, emphasised the laborious process of disentangling genuine brain activity from other signals, noting that machine learning engineers had to participate in data collection to understand what worked. Guilhem Dupont, CEO and Founder of Indivi, stated that the acquisition marks a new chapter, with Cogitat's EEG foundation model decoding brain activity and revealing signals closer to underlying biology than ever before.
Dr Ponniah added that NeuroRVQ works across every brain's unique language without individual training to identify subtle changes in brain activity. This addresses a significant translational gap in neuroscience. He expressed enthusiasm for taking the work to the next level with Indivi, validating the technology and delivering value.
NeuroRVQ will be presented at the 40th Annual Conference on Neural Information Processing Systems (NeurIPS), taking place from 6-12 December 2026.




