Ashkan Pirmani, Ilse Vermeulen, Goran Vinterhalter +7 more
Federated learning lets institutions train a shared model without moving their data anywhere, which is exactly what health and life sciences research needs under strict privacy rules. The methods themselves are maturing quickly.
The authors point out that the obstacle has moved earlier in the process. A team deciding to start a federated project runs into a scattered landscape of frameworks, governance obligations and unfamiliar roles, with no structured starting point suited to their own background. The blocker is not the algorithm any more, it is the first week.
FLKit is an open, community-maintained onboarding toolkit built for that gap, taking a multidisciplinary team through the process. It is an unglamorous contribution and probably a high-leverage one, since the projects that never begin do not show up in anybody's results table.
Federated learning lets institutions train shared models without moving their data, which makes it a natural fit for health and life sciences research under strict privacy regulation. The methods are maturing fast, but the practical barrier now comes earlier: a team starting a federated project meets a scattered mix of frameworks, governance obligations, and unfamiliar roles, with no structured place to begin that fits its own background. FLKit closes that gap. It is an…
Sensory Restoration via Brain-Computer Interfaces: A Unified 2 x 2 Framework and Convergence Roadmap
arXiv (BCI) · June 12, 2026Test-Time Adaptation of Spiking Neural Networks for Intracortical Neural Decoding using Membrane Potential Alignment
arXiv (neural decoding) · June 12, 2026Decoding Semantic Categories from Picture-Naming EEG
arXiv (BCI) · July 16, 2026Dendrite: A Real-Time Python Application for Online Brain-Computer Interface Research and Development