aiqbench takeAI Products

Generalist AI's GEN-1.5 demonstrates a significant leap in robot foundation models by enabling one-shot physical task learning through simple sensorimotor demonstrations without fine-tuning or gradient updates. While currently restricted to research partnerships with no public weights available, this approach suggests a viable path toward scalable, adaptable robotic manipulation that relies on continuous pretraining rather than task-specific programming.

Source coveringMarkTechPost

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Generalist AI Releases GEN-1.5: A Robot Foundation Model That Learns New Tasks From One 3–12 Second Demo

MarkTechPostAugust 24, 20265 min read

Generalist AI has released GEN-1.5, a robot foundation model that learns a new physical task from a single demonstration. Drop 3–12 seconds of sensorimotor data into its 30-second context window, and the robot performs the task. No gradient updates, no fine-tuning, no task-specific programming. Across 10 diverse manipulation tasks, this one-shot in-context prompting averaged 59% […] The post Generalist AI Releases GEN-1.5: A Robot Foundation Model That Learns New Tasks From One 3–12 Second Demo appeared first on MarkTechPost.

Generalist AI has released GEN-1.5, a robot foundation model that learns a new physical task from a single demonstration. Drop 3–12 seconds of sensorimotor data into its 30-second context window, and the robot performs the task. No gradient updates, no fine-tuning, no task-specific programming. Across 10 diverse manipulation tasks, this one-shot in-context prompting averaged 59% success (±10% std. dev.) straight from the pretrained model. Ten gradient steps on five minutes of data per task raised that to 83% (±9%). Generalist calls the…

Excerpt shown under the publisher's RSS terms · 82 words · full text and figures are on the publisher's site

Read at MarkTechPost ↗Ask about this article