General Instinct
ActiveDeployable Physical AI on Any Edge Device.
Founders · 2
worked on Siemens' first multimodal foundation model, secured 2 patents on tardigrade proteins as a junior in high school, now building edge intelligence for physical AI.
Worked on robot learning and multimodal foundation models at DeepMind, UCL, and Tsinghua, with research recognized at ICML and ICRA. Now building the deployment layer for physical AI.
Launch
Deploy frontier AI models onto constrained edge hardware for robots, drones, and physical AI systems.
General Instinct launches Instinct Edge, a no-code pipeline that distills, quantizes, and deploys frontier AI models to edge hardware (Jetson, mobile NPUs, ARM CPUs, Apple Neural Engine, Snapdragon) with specified latency budgets, enabling on-device inference for drones, robots, and IoT without cloud calls.
Formerly “Bitstream”
Related startups
Enabling physical AI at scale.
The default way of running on-device AI at Scale
