Development
1X trains a robot world model on generated video
Claim
1X launched 1XWM, a world model trained on robot actions derived from text-conditioned video generation rather than static image-language inputs.
Reporting date: (not necessarily the event date)
Sources
Attribution and reporting linked by this record; links do not imply independent verification.
- Welcome to January 13, 2026 (theinnermostloop.substack.com)
Cite or correct this record
Suggest a correction — opens a GitHub draft for you to review and submit.