1X World Model (1XWM)
Two stages: 1XWM as a policy evaluator (2025-06-16) and as a NEO policy (2026-01-12). No API or weights. TechCrunch coverage: https://techcrunch.com/2026/01/13/neo-humanoid-maker-1x-releases-world-model-to-help-bots-learn-what-they-see/
- Input
- text, image, video
- Output
- video, action
- License
- proprietary
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Not available (internal; runs NEO policies) | — | www.1x.tech/discover/world-model-self-learning | docs |
Notable capabilities (3)
- Video world model used as the robot policy: Given a text prompt, a 14B generative video model fine-tuned on NEO imagines ~5 s of future video; an inverse-dynamics model converts it into actions executed on NEO (≈11 s per rollout on multi-GPU inference). source
- Learns from human egocentric video: Trained with ~900 h of egocentric human video plus ~70 h of NEO data (and 400 h of unfiltered robot data for the IDM); generalizes to some objects and motions absent from NEO task data. Grasping ~80% success; pouring 0%; best-of-8 generations raised 'pull tissue' from 30% to 45%. source
- World model for policy evaluation: The June 2025 version was an action-conditioned simulator used to rank policies without physical tests (1X: 70% world-model accuracy picks the better policy ~90% of the time). source
Timeline entry
- 1X turns its video world model into a robot policy for NEO ★★★
On 2026-01-12 1X showed the 1X World Model (1XWM) acting as NEO's policy: a 14B video model imagines the next ~5 s from a text prompt and an inverse-dynamics model turns that video into robot actions, letting the home humanoid attempt some objects and motions absent from its robot training data.