Paper deep dive
Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
Wenkang Qin, Yukun Zhou, Noah Shen, Jisong Cai, Dongxiao Mao, Baicheng Li, Yue Zhang, Wei Sui
Intelligence
Status: succeeded | Model: Gemma-4-26B-A4B | Prompt: intel-v1 | Confidence: 96%
Last extracted: 9/23/2026, 4:06:36 AM
Summary
The paper titled 'Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI' proposes a data-driven robot simulator based on a joint-trajectory-conditioned autoregressive diffusion model. It highlights capabilities such as streaming open-ended rollout, low-latency generation (24 FPS), and scalable multi-view robot control. However, the paper was officially withdrawn by the authors due to incompleteness and lack of unanimous agreement among co-authors regarding its release.
Entities (6)
Relation Signals (7)
Wenkang Qin → authored → Uranus
confidence 99% · Authors:Wenkang Qin... This paper titled... by Wenkang Qin
arXiv:2609.24815 → hasstatus → withdrawn
confidence 99% · This submission is being withdrawn... (withdrawn)
Yukun Zhou → withdrew → arXiv:2609.24815
confidence 99% · This submission is being withdrawn by Yukun Zhou
Uranus → uses → autoregressive diffusion model
confidence 95% · Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned autoregressive diffusion model.
Uranus → hascapability → scalable, extensible robot control
confidence 90% · (3) scalable, extensible robot control, providing a unified interface...
Uranus → hascapability → streaming, open-ended rollout
confidence 90% · Uranus offers three key capabilities: (1) streaming, open-ended rollout...
Uranus → hascapability → low-latency generation
confidence 90% · (2) low-latency generation, achieving 24 FPS after inference optimization
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
Abstract:Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned autoregressive diffusion model. Uranus offers three key capabilities: (1) streaming, open-ended rollout, which receives future joint-position trajectories online and autoregressively generates one latent frame per step, corresponding to four RGB frames, without a fixed horizon; (2) low-latency generation, achieving 24 FPS after inference optimization; and (3) scalable, extensible robot control, providing a unified interface for synchronized multi-view generation across diverse robot embodiments and camera configurations. We conduct comprehensive quantitative and qualitative evaluations on both in-distribution and out-of-distribution data, providing an objective assessment of Uranus and clearly identifying its current limitations. We release the code and model weights to empower the community with practical tools and insights.
Tags
Links
- Source: https://arxiv.org/abs/2609.24815v2
- Canonical: https://arxiv.org/abs/2609.24815v2
PDF not stored locally. Use the link above to view on the source site.
Full Text
4,964 characters extracted from source content.
Expand or collapse full text
Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Robotics arXiv:2609.24815v2 (cs) This paper has been withdrawn by Yukun Zhou [Submitted on 21 Sep 2026 (v1), last revised 22 Sep 2026 (this version, v2)] Title:Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI Authors:Wenkang Qin, Yukun Zhou, Noah Shen, Jisong Cai, Dongxiao Mao, Baicheng Li, Yue Zhang, Wei Sui View a PDF of the paper titled Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI, by Wenkang Qin and 7 other authors No PDF available, click to view other formats Abstract:Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned autoregressive diffusion model. Uranus offers three key capabilities: (1) streaming, open-ended rollout, which receives future joint-position trajectories online and autoregressively generates one latent frame per step, corresponding to four RGB frames, without a fixed horizon; (2) low-latency generation, achieving 24 FPS after inference optimization; and (3) scalable, extensible robot control, providing a unified interface for synchronized multi-view generation across diverse robot embodiments and camera configurations. We conduct comprehensive quantitative and qualitative evaluations on both in-distribution and out-of-distribution data, providing an objective assessment of Uranus and clearly identifying its current limitations. We release the code and model weights to empower the community with practical tools and insights. Comments: This submission is being withdrawn because the manuscript is incomplete and further work on this research is still ongoing. In addition, the authors have not reached unanimous agreement on releasing the current version, and some co-authors do not agree with the release of this version. For these reasons, we request withdrawal of this submission Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI) Cite as: arXiv:2609.24815 [cs.RO] (or arXiv:2609.24815v2 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2609.24815 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yukun Zhou [view email] [v1] Mon, 21 Sep 2026 16:06:16 UTC (20,402 KB) [v2] Tue, 22 Sep 2026 09:34:42 UTC (1 KB) (withdrawn) Full-text links: Access Paper: View a PDF of the paper titled Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI, by Wenkang Qin and 7 other authorsWithdrawn No license for this version due to withdrawn Current browse context: cs.RO < prev | next > new | recent | 2026-09 Change to browse by: cs cs.AI References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?) mathjaxToggle(); We gratefully acknowledge support from our major funders, member institutions, , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from