{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/1x-world-model/","md":"https://postcutoff.com/m/1x-world-model/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"1x-world-model","name":"1X World Model (1XWM)","org":"1X Technologies","family":"1X World Model","released":"2026-01-12","status":"preview","type":"world-model","modality_in":["text","image","video"],"modality_out":["video","action"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Not available (internal; runs NEO policies)","url":"https://www.1x.tech/discover/world-model-self-learning","docs":"https://www.1x.tech/1x-world-model.pdf"}],"capabilities":[{"name":"Video world model used as the robot policy","detail":"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).","first":false,"discovered":"launch","source":"https://www.1x.tech/discover/world-model-self-learning"},{"name":"Learns from human egocentric video","detail":"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%.","first":false,"discovered":"launch","source":"https://www.1x.tech/discover/world-model-self-learning"},{"name":"World model for policy evaluation","detail":"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).","first":false,"discovered":"launch","source":"https://www.1x.tech/discover/redwood-ai-world-model"}],"entry":"2026-01-12-1x-world-model-policy","notes":"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/","verified":null,"body_md":null,"page_url":"https://postcutoff.com/m/1x-world-model/","standing":{"kind":"world","newer_count":3,"newer":[{"id":"genie-4","name":"Genie 4","org":"Google DeepMind","released":"2026-10-27","page_url":"https://postcutoff.com/m/genie-4/"},{"id":"xiaomi-robotics-u0","name":"Xiaomi-Robotics-U0 (38B) / U0-4B","org":"Xiaomi","released":"2026-07-13","page_url":"https://postcutoff.com/m/xiaomi-robotics-u0/"},{"id":"cosmos-3","name":"Cosmos 3 (Nano / Super)","org":"NVIDIA","released":"2026-06-01","page_url":"https://postcutoff.com/m/cosmos-3/"}],"before":null,"after":null,"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights."}}