Robot foundation model from Generalist AI that learns new tasks in-context from a short demonstration.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
GEN-1.5 is an embodied foundation model from Generalist AI, a company building general intelligence for the physical world. Per the vendor, it can learn a new task in-context from as little as 12 seconds of demonstration data, or adapt with 1 to 10 gradient steps on a few minutes of data. These abilities are attributed to pretraining on large-scale physical experience.
A YouTube creator summary reports 59% success across 10 tasks in the one-shot setting, rising to 83% with about 5 minutes of additional data. These figures come from a secondary source and were not verified against a primary paper. The predecessor, GEN-1, is described as supporting a broad range of end effectors, so one model can transfer across different robot hands and grippers.
GEN-1.5 is a research and product model, not a publicly downloadable release. No public API, pricing, weights or documentation were found. Access appears to be through direct engagement with Generalist.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Robot foundation model that can attempt a task from a single 3-12 second demonstration. It reaches 59% success across 10 tasks one-shot and 83% with about 5 minutes of extra data.
Closest neighbours by meaning, not just by category.
Model · Skild AI
Skild AI's robotic foundation model that performs new tasks from a single video demonstration, with no fine-tuning.
Research
Research framework letting a frozen VLM agent learn robot tasks in context from videos, images and feedback, no fine-tuning.
Model · Perceptron
Perceptron's vision-language model for physical AI, covering perception, physical reasoning and robot action prediction.
Research · Skild AI
Skild AI research result: humanoid soccer policy trained by self-play in Isaac Sim on the S1 model, transferred to a real robot.
Research · Google DeepMind
Google DeepMind research that turns a text-to-video diffusion model into a single feed-forward, multi-task vision model.
Model · Unitree
Unitree's 6B-parameter vision-language-action foundation model for humanoid robots, covering 64 tabletop and whole-body tasks.
