New York-based Synchron wants to advance BCI from supervised to self-supervised learning. Through a collaboration with Nvidia, the company can accelerate the transition by combining large-scale neural data with advanced AI computing.
The news was part of a host of medtech AI announcements this week as Nvidia holds its GTC 2025 event in San Jose, California. (We have a full roundup of medtech AI news out of Nvidia’s “Super Bowl of AI.”)
Synchron built its BCI technology on the Nvidia Holoscan platform. It says the collaboration, announced in January, could redefine the possibilities of real-time neural interaction and intelligent edge processing. Holoscan offers a unified framework that supports diverse AI models and data modalities. It also features an optimized application framework, with seamless sensor I/O integration, GPU-direct data ingestion, accelerated computing and real-time AI.
The company has demonstrated how its AI-enabled BCI could be displayed on the Apple Vision Pro. This allows individuals to control digital and physical environments using Synchron’s Stentrode direct thought-control technology. (A video demonstrating this feat is below.)
Synchron’s BCI system is stent-based and uniquely delivered through an endovascular approach. It taps into blood vessels to capture signals from the brain. It could restore the capability for severely paralyzed patients to control personal devices with hands-free point-and-click. The company could be the leader in a growing BCI space with a massive market opportunity.
“We are building a brain foundation model using generative pre-training techniques that learn directly from neural data—abstracting human cognition at its source – to create features that improve our user’s lives,” said Dr. Tom Oxley, CEO and founder, Synchron. “This is possible because of our ability to scale large datasets, by making BCI as common as a stent insertion.”
More about the collaboration between Synchron and Nvidia
Synchron said it based its collaboration with Nvidia around three major technological milestones.
First, the companies aim to deliver motor interference powered by Holoscan. This could enable real-time neural decoding with minimal latency. Nvidia Holoscan enhances on-device edge computation to enable faster, more precise motor interference in Synchron’s BCI. The companies say this allows users to seamlessly control digital environments through thought alone.
Second, Nvidia Cosmos could deliver context-aware interaction to integrate environmental awareness. This creates physics-bound, photorealistic simulations of domestic environments to generate richly labeled datasets to enhance motor inference accuracy, adaptability and fine-tuning. The system produces higher-dimensional inference, making interactions more predictive, adaptive and intuitive.
Third, the companies will train Chiral based on deidentified data. As a pre-trained brain model, Chiral will abstract human conditions from large-scale neural data to elevate BCI, brain health and future AI systems.
Synchron says the breakthrough is only possible at scale, made possible by its minimally invasive BCI delivery. The scalability enables population-level neural data collection to train brain intelligence models.
“We are witnessing a new computing paradigm, where technology is no longer just responding to people—it’s empowering them in entirely new ways,” said David Niewolny, Senior Director of Business Development at NVIDIA. “By combining its breakthrough BCI technology with NVIDIA AI and Omniverse, Synchron is helping to deliver new possibilities for individuals with disabilities, enabling greater independence, communication, and connection with the world.”
