{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2026-07-13-xiaomi-robotics-u0/","md":"https://postcutoff.com/e/2026-07-13-xiaomi-robotics-u0/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":"2026-07-13-xiaomi-robotics-u0","date":"2026-07-13","date_precision":"day","short_title":"Xiaomi open-sources Xiaomi-Robotics-U0, a 38B unified world model that generates multi-view robot scenes and training data","deck":null,"takeaway":null,"category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"arXiv 2607.11643: Xiaomi-Robotics-U0","url":"https://arxiv.org/abs/2607.11643","type":"paper","group":"primary","domain":"arxiv.org"},{"n":2,"title":"Hugging Face: Xiaomi-Robotics-U0","url":"https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-U0","type":"code","group":"primary","domain":"huggingface.co"},{"n":3,"title":"Hugging Face: Xiaomi-Robotics-U0-4B","url":"https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-U0-4B","type":"code","group":"primary","domain":"huggingface.co"},{"n":4,"title":"Project page","url":"https://robotics.xiaomi.com/xiaomi-robotics-u0.html","type":"official","group":"primary","domain":"robotics.xiaomi.com"}],"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Xiaomi"],"title":"Xiaomi open-sources Xiaomi-Robotics-U0, a 38B unified world model that generates multi-view robot scenes and training data","summary":"On 2026-07-13 Xiaomi released Xiaomi-Robotics-U0 (arXiv 2607.11643, Apache-2.0), a 38B autoregressive model initialized from Emu3.5 that handles text-to-image, image editing, multi-view embodied scene generation, embodied transfer and embodied video in one next-token framework; its synthetic data raised π0.5's out-of-distribution real-world success from 36.9% to 63.2%. A smaller U0-4B followed on 2026-09-08.","key_facts":["38B params per paper (HF README says 34B); initialized from Emu3.5; shared discrete visual tokenizer","Authors: beats GPT-Image-2.0 in human evals of embodied scene generation and transfer; #1 on World Arena for embodied video generation","Used as a data engine: π0.5 OOD success 36.9% -> 63.2% on hard real-world manipulation tasks","FlashAR decoding: 5.44 s per 1024x1024 image on one H20 (82.86x faster than eager AR)","U0-4B, U0-Sequence, U0-4B-Sequence weights and FSDP training code released 2026-09-08"],"key_numbers":[],"tags":["world-model","robotics","synthetic-data","open-weights","china","image-generation"],"science":null,"body_md":"## What happened\n\nThree days before its Xiaomi-Robotics-1 VLA, Xiaomi released an open world model that treats robot-scene generation as an extension of general image and video generation. The goal is to keep the general visual knowledge of a large pretrained generator while adding multi-view consistency and robot embodiment constraints.\n\n## Why it matters\n\nLike NVIDIA's Cosmos, it bets that generated data can offset the shortage of real robot data. Xiaomi reports a large gain in π0.5's generalization from U0 data, which is a concrete measure of whether synthetic data helps real robots. The figures are the authors' own.","disputed":[],"related":[{"id":"2026-07-16-xiaomi-robotics-1","url":"https://postcutoff.com/e/2026-07-16-xiaomi-robotics-1/","date":"2026-07-16","date_precision":"day","short_title":"Xiaomi open-sources Xiaomi-Robotics-1, a VLA trained on 100K+ hours of real trajectories","deck":null,"takeaway":"It makes a 100K-hour-scale robot model openly available, narrowing the data gap between closed US labs and open Chinese releases.","category":"open-source","category_label":"Open source","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":3,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Xiaomi"]},{"id":"2026-06-01-nvidia-cosmos-3-open-release","url":"https://postcutoff.com/e/2026-06-01-nvidia-cosmos-3-open-release/","date":"2026-06-01","date_precision":"day","short_title":"NVIDIA releases Cosmos 3, an open omni-model for physical AI","deck":null,"takeaway":"It is the largest open world model aimed at robotics and autonomous vehicles.","category":"open-source","category_label":"Open source","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["NVIDIA"]}],"people":[],"posts":[],"videos":[],"models":[{"id":"xiaomi-robotics-u0","name":"Xiaomi-Robotics-U0 (38B) / U0-4B","url":"https://postcutoff.com/m/xiaomi-robotics-u0/"}],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":74,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":13,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":104,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":43,"in_training_data":false}],"short_url":null}