{"schema":"postcutoff/event@1","as_of":"2026-10-12T22:30:00+02:00","url":"https://postcutoff.com/e/2026-07-14-beingbeyond-being-m0-7-latent-world-action-model/","md":"https://postcutoff.com/e/2026-07-14-beingbeyond-being-m0-7-latent-world-action-model/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-07-14-beingbeyond-being-m0-7-latent-world-action-model","date":"2026-07-14","date_precision":"day","short_title":"BeingBeyond's Being-M0.7","deck":"A latent world-action model for humanoid whole-body loco-manipulation, pre-trained on 10,000+ hours of human data","takeaway":"Chinese robotics startup BeingBeyond published a technical report on Being-M0.7 (dated July 14, 2026), a latent world-action model for humanoids.","category":"robotics","category_label":"Robotics","importance":2,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":[{"n":1,"title":"BeingBeyond: Being-M0.7 project page","url":"https://research.beingbeyond.com/being-m07","type":"official","group":"primary","domain":"research.beingbeyond.com"},{"n":2,"title":"Being-M0.7 technical report (PDF)","url":"https://research.beingbeyond.com/being-m07/being-m07.pdf","type":"paper","group":"primary","domain":"research.beingbeyond.com"},{"n":3,"title":"Pandaily: BeingBeyond's Being-M0.7 uses 10,000 hours of human video to teach humanoids to walk and grasp","url":"https://pandaily.com/beingbeyond-being-m0-7-latent-world-action-model-humanoid-loco-manipulation-simple-71-1","type":"press","group":"press","domain":"pandaily.com"}],"official":2,"filed":"2026-10-12","updated":"2026-10-12","orgs":["BeingBeyond"],"title":"BeingBeyond's Being-M0.7: a latent world-action model for humanoid whole-body loco-manipulation, pre-trained on 10,000+ hours of human data","summary":"Chinese robotics startup BeingBeyond published a technical report on Being-M0.7 (dated July 14, 2026), a latent world-action model for humanoids. It learns a video-and-motion prior from more than 10,000 hours of human-centric data, predicts future egocentric visual states and whole-body motion in latent space, and a small action expert turns them into commands for a Unitree G1. The project page reports no benchmark scores; Pandaily covered it on October 12, 2026.","key_facts":["Technical report 'Being-M0.7: A Latent World-Action Model for Humanoid Robots', dated July 14, 2026; authors Junpeng Yue, Boyuan Li, Yuxuan Wang and others, last author Zongqing Lu","Pre-training: more than 10,000 hours of human-centric mixed-modality data (raw, before filtering and segmentation)","Design: a pretrained prior predicts future egocentric visual states and a compact whole-body motion sequence; a lightweight future-conditioned action expert outputs low-level action chunks","Robot: Unitree G1 humanoid; robot data collected by VR teleoperation with a motion-tracking controller at 50 Hz","No arXiv listing was found; the project page gives no benchmark scores or baselines and does not mention a code or weights release"],"key_numbers":[],"tags":["robotics","humanoid","world-action-model","loco-manipulation","human-video","unitree-g1","china"],"science":null,"body_md":"## What happened\n\nBeing-M0.7 extends the company's earlier models for tabletop manipulation to whole-body movement: walking, reaching and\ncarrying with one policy. Instead of generating future video frames, it predicts the future scene and body motion in a latent\nspace and then converts that plan into robot commands. The model is first trained on human video and motion data and then\npost-trained on a small amount of teleoperated robot data.\n\nThe Pandaily article (October 12) was readable only as a headline; its URL mentions a score of 71.1 on a benchmark called\nSIMPLE, which the project page does not report and which is therefore not stated here as a fact.\n\n## Why it matters\n\nHuman video is far cheaper to collect than robot teleoperation data. Several Chinese labs (BeingBeyond, Robotera) now train\n\"world-action\" models on it and use robot data only for the last step.","disputed":[],"related":[{"id":"2026-10-10-robotera-vpp2-world-action-model","url":"https://postcutoff.com/e/2026-10-10-robotera-vpp2-world-action-model/","date":"2026-10-10","date_precision":"day","short_title":"Robotera's open-source VPP2 world action model tops the RoboDojo benchmark and scores 58.5% zero-shot on a real ALOHA robot vs 40% for pi0.5","deck":null,"takeaway":"It is a strong open-source data point for world-model-based robot control.","category":"robotics","category_label":"Robotics","importance":2,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":1,"official":0,"filed":"2026-10-11","updated":"2026-10-11","orgs":["Robotera"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-12","type":"filed","text":"Created (evening)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-12","run":null,"sources_read":null,"updated":"2026-10-12","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":75,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":14,"in_training_data":false},{"model_id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","cutoff":"2026-03","days_after":105,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":44,"in_training_data":false}],"short_url":null}