Generalist GEN-1.5
Released 6 days before Skild S1, which makes a similar one-video in-context claim for long-horizon tasks. Company-reported. Video: https://www.youtube.com/watch?v=1cllCVK-9lo
- Input
- video, image, text
- Output
- action
- License
- proprietary
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Generalist AI partners (no public access announced) | — | generalistai.com/blog/gen-1.5 | — |
Notable capabilities (2)
- FIRST One-shot learning of dexterous closed-loop tasks: Learns new tasks in-context from one demonstration video: 59% average success one-shot across 10 tasks; 83% with few-shot adaptation (10 gradient steps on 5 minutes of data). Generalist says it is the first model it knows of to show this across a wide range of dexterous closed-loop tasks. source
- 30-second video memory, 100 Hz actions: Takes video (30 s memory window), sensors, language and proprioception and outputs 100 Hz action trajectories. source
Timeline entry
- Generalist GEN-1.5 learns dexterous robot tasks from one demonstration ★★★
On 2026-08-19 Generalist released GEN-1.5, which learns new dexterous closed-loop tasks in-context from a single demonstration video (59% average success across 10 tasks) and reaches 83% with 10 gradient steps on 5 minutes of data.