GEN-1.5 Robot Model Shows One-Shot Learning, Expert Calls It Embodied AI Step Change
E0M · x · 2026-08-20
GeneralistAI released GEN-1.5, a one-shot learner focused on the physical world. It can learn new tasks in seconds and generalize from demonstrations. This capability emerged from large-scale pretraining on physical data. Researchers describe it as the holy grail of in-context learning for robot control, with an impact comparable to the first experience with GPT-3.
Related event: Generalist AI Unveils GEN-1.5: One-Shot Robot Learning in Seconds(10 posts)→
More from Embodied
- Zetta ζ: Closed-Loop Embodied Harness Evolves Critics and Recovery Skills Online — Xin Ding · 2026-08-20
- SoftVTBench: A Deformation-Aware Visuo-Tactile Dataset for Deformable-Object Manipulation — TuojingAI · 2026-08-20
- Robotics manipulation harder than pure vision due to problem definition — chris_j_paxton · 2026-08-20
- Zipline on drone noise mitigation and preventing delivery screw-ups — kscottz · 2026-08-20
- Tesla aims for Optimus commercial sales in 2H27; FSD V15 hailed as major leap — chrisfirst · 2026-08-20
- Beijing robot output up 2.3x in H1; Zhiyuan A3 wins China & EU certifications — 创业邦 · 2026-08-20