Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate

• URL: http://arxiv.org/abs/2603.26360v1
• Date: Fri, 27 Mar 2026 12:37:44 GMT
• Title: Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate
• Abstract summary: In this report we describe a set of practical techniques to achieve the end-to-end result of running a VLA-driven robot at an impressive speed in real world tasks.<n>The stack of technology ranges across calibration, planning & control, and learning based method to identify optimal execution speed.<n>In the tasks we show, the robot even executes in a speed on par with casual human operation and approaching the hardware limit of our lightweight arm.
• Score: 17.203916358155286
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In deployment of the VLA models to real-world robotic tasks, execution speed matters. In previous work arXiv:2510.26742 we analyze how to make neural computation of VLAs on GPU fast. However, we leave the question of how to actually deploy the VLA system on the real robots open. In this report we describe a set of practical techniques to achieve the end-to-end result of running a VLA-driven robot at an impressive speed in real world tasks that require both accuracy and dexterity. The stack of technology ranges across calibration, planning & control, and learning based method to identify optimal execution speed. In the tasks we show, the robot even executes in a speed on par with casual human operation and approaching the hardware limit of our lightweight arm. The unaccelerated videos and inference traces are provided in https://dexmal.github.io/realtime-vla-v2/.

Related papers

• Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models [120.24139942108405]
  Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models.<n>Under a fixed robot-data budget, continued pre-training must turn limited trajectories into transferable visual-action knowledge.<n>We propose VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data.
  arXiv  Detail & Related papers  (2026-08-27T17:59:40Z)
• Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation [13.410971154780588]
  State-of-the-art vision-language-action (VLA) models exhibit strong semantic understanding, instruction following and task behavior.<n>When deployed on new robots, even minor mismatches in hardware configuration relative to pretraining can cause severe performance drops.<n>We propose a self-supervised method that generates online interaction rollouts from the zero-shot VLA as additional training data for finetuning.
  arXiv  Detail & Related papers  (2026-08-19T23:02:07Z)
• DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation [7.958222488148539]
  We propose DySL-VLA, a novel framework that addresses computational cost by dynamically skipping VLA layers based on each action's importance.<n>Our experiments indicate that DySL-VLA achieves 2.1% improvement in success length over Deer-VLA on the Calvin dataset.
  arXiv  Detail & Related papers  (2026-02-26T11:34:36Z)
• 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)
• A Pragmatic VLA Foundation Model [66.76609538850478]
  We develop LingBot-VLA with around 20,000 hours of real-world data from 9 popular dual-arm robot configurations.<n>Our model achieves clear superiority over competitors, showcasing its strong performance and broad generalizability.<n>To advance the field of robot learning, we provide open access to the code, base model, and benchmark data.
  arXiv  Detail & Related papers  (2026-01-26T17:08:04Z)
• Robotic VLA Benefits from Joint Learning with Motion Image Diffusion [114.60268819583017]
  Vision-Language-Action (VLA) models have achieved remarkable progress in robotic manipulation by mapping multimodal observations and instructions directly to actions.<n>We propose joint learning with motion image diffusion, a novel strategy that enhances VLA models with motion reasoning capabilities.<n> Experiments in both simulation and real-world environments demonstrate that joint learning with motion image diffusion improves the success rate of pi-series VLAs to 97.5%.
  arXiv  Detail & Related papers  (2025-12-19T19:07:53Z)
• VLA-0: Building State-of-the-Art VLAs with Zero Modification [8.916252953026888]
  Vision-Language-Action models (VLAs) hold immense promise for enabling generalist robot manipulation.<n>This work introduces VLA-0 to investigate the simplest strategy of representing actions directly as text.<n>We find that VLA-0 is not only effective; it is surprisingly powerful.
  arXiv  Detail & Related papers  (2025-10-15T00:31:10Z)
• VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning [14.099306230721245]
  We present VLA-RL, an exploration-based framework that improves on online collected data at test time.<n>We fine-tune a pretrained vision-language model as a robotic process reward model, which is trained on pseudo reward labels annotated on automatically extracted task segments.<n>VLA-RL enables OpenVLA-7B to surpass the strongest finetuned baseline by 4.5% on 40 challenging robotic manipulation tasks in LIBERO.
  arXiv  Detail & Related papers  (2025-05-24T14:42:51Z)
• ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis [39.50916343607966]
  ReBot is a novel real-to-sim-to-real approach for scaling real robot datasets.<n>We show that ReBot significantly enhances the performance and robustness of vision-language-action (VLA) models.
  arXiv  Detail & Related papers  (2025-03-15T16:47:25Z)
• FAST: Efficient Action Tokenization for Vision-Language-Action Models [98.15494168962563]
  We propose a new compression-based tokenization scheme for robot actions, based on the discrete cosine transform.<n>Based on FAST, we release FAST+, a universal robot action tokenizer, trained on 1M real robot action trajectories.
  arXiv  Detail & Related papers  (2025-01-16T18:57:04Z)
• TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies [95.30717188630432]
  We introduce visual trace prompting to facilitate VLA models' spatial-temporal awareness for action prediction.<n>We develop a new TraceVLA model by finetuning OpenVLA on our own collected dataset of 150K robot manipulation trajectories.<n>We present a compact VLA model based on 4B Phi-3-Vision, pretrained on the Open-X-Embodiment and finetuned on our dataset.
  arXiv  Detail & Related papers  (2024-12-13T18:40:51Z)
• LLaRA: Supercharging Robot Learning Data for Vision-Language Policy [56.505551117094534]
  We introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations.<n>First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets.<n>We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control.
  arXiv  Detail & Related papers  (2024-06-28T17:59:12Z)

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.