Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

• URL: http://arxiv.org/abs/2607.15330v2
• Date: Wed, 22 Jul 2026 11:38:14 GMT
• Title: Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
• Abstract summary: Xiaomi-Robotics-1 is a vision-language-action (VLA) model for mobile manipulation.<n>It follows diverse language instructions to perform a wide range of mobile manipulation tasks.<n>It efficiently adapts to novel downstream tasks with minimal fine-tuning data.
• Score: 36.86989207036016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulation tasks in unseen environments out-of-the-box, and (2) efficiently adapting to novel downstream tasks with minimal fine-tuning data. We propose a two-stage training recipe consisting of pre-training and post-training. During pre-training, we imbue the model with broad and generalizable action-generation capabilities by training on over 100k hours of real-world manipulation trajectories collected via UMI devices. Crucially, we develop a scalable auto-labeling pipeline that annotates trajectory clips with natural languages describing scene state transitions, providing rich and precise conditioning for action learning. During post-training, we aim to align these capabilities with robot embodiments and imperative instructions that humans naturally use to prompt robots. Extensive experiments demonstrate strong scaling behavior. Xiaomi-Robotics-1 consistently improves with increased data scales and model sizes during pre-training. This scaling behavior directly transfers to post-training, where a stronger pre-training model yields better out-of-the-box real-robot performance in unseen environments. Furthermore, Xiaomi-Robotics-1 serves as a strong robot foundation policy that can be efficiently fine-tuned on complex, dexterous tasks with high data efficiency. Across multiple simulation benchmarks, Xiaomi-Robotics-1 outperforms state-of-the-art methods. Notably, it establishes a new state-of-the-art with a 57.4% success rate on RoboCasa365, surpassing the previous best of 46.6%. Furthermore, it achieves an average score of 20.07 on RoboDojo, significantly outperforming the prior state-of-the-art (13.07). Code and model checkpoints will be released. Project page: https://robotics.xiaomi.com/xiaomi-robotics-1.html

Related papers

• ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training [93.39352617578857]
  We introduce ZimaBlue, a framework for learning generalizable World Action Models from large-scale video.<n>ZimaBlue follows a three-stage training curriculum, first performing causal embodied video pre-training on large-scale human and robot egocentric videos.<n>ZimaBlue further delivers strong performance across multiple benchmarks, with particularly pronounced gains on unseen tasks.
  arXiv  Detail & Related papers  (2026-08-31T18:09:52Z)
• From Foundation to Application: Improving VLA Models in Practice [62.1552185059214]
  We present LingBot-VLA 2.0, which advances LingBot-VLA through improvements in three functional domains.<n>Compared to the previous version, we revamp the data processing pipeline and curate around 60,000 hours of data for pretraining.<n>In particular, our system accommodates degrees of freedom for the heads, waists, mobile bases, and dexterous hands, thereby empowering the robots to tackle more complex tasks in practical scenarios.
  arXiv  Detail & Related papers  (2026-07-07T15:33:12Z)
• World Action Models are Zero-shot Policies [111.91938055103633]
  We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone.<n>By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data.<n>We demonstrate two forms of cross-embodiment transfer: video-only demonstrations from other robots or humans yield a relative improvement of over 42% on unseen task performance.
  arXiv  Detail & Related papers  (2026-02-17T15:04:02Z)
• Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution [32.93468341343403]
  We introduce Xiaomi-Robotics-0, an advanced vision-language-action (VLA) model optimized for high performance and fast and smooth real-time execution.<n>Xiaomi-Robotics-0 is first pre-trained on large-scale cross-embodiment robot trajectories and vision-language data, endowing it with broad and generalizable action-generation capabilities.<n>We evaluate Xiaomi-Robotics-0 extensively in simulation benchmarks and on two challenging real-robot tasks that require precise and dexterous bimanual manipulation.
  arXiv  Detail & Related papers  (2026-02-13T07:30:43Z)
• InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy [138.89177083578213]
  We introduce InternVLA-M1, a unified framework for spatial grounding and robot control.<n>InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data, and (ii) spatially guided action post-training.<n>Results: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka.
  arXiv  Detail & Related papers  (2025-10-15T17:30:05Z)
• Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation [25.09113607683987]
  We introduce GR-1, a GPT-style model designed for multi-task language-conditioned visual robot manipulation. GR-1 takes as inputs a language instruction, a sequence of observation images, and a sequence of robot states. It predicts robot actions as well as future images in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-12-20T16:00:43Z)
• RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation [33.10577695383743]
  We propose a multi-embodiment, multi-task generalist agent for robotic manipulation called RoboCat. This data spans a large repertoire of motor control skills from simulated and real robotic arms with varying sets of observations and actions. With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples.
  arXiv  Detail & Related papers  (2023-06-20T17:35:20Z)
• Robot Learning with Sensorimotor Pre-training [98.7755895548928]
  We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. We find that sensorimotor pre-training consistently outperforms training from scratch, has favorable scaling properties, and enables transfer across different tasks, environments, and robots.
  arXiv  Detail & Related papers  (2023-06-16T17:58:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.