Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack

• URL: http://arxiv.org/abs/2606.14409v1
• Date: Fri, 12 Jun 2026 12:45:18 GMT
• Title: Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack
• Abstract summary: Hy-Embodied-0.5-VLA is an end-to-end system that spans the full robot learning stack.<n>It includes data collection, model design, continued pre-training and supervised fine-tuning, RL post-training, and real-world deployment.
• Score: 68.26410985517266
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this report, we present Hy-Embodied-0.5-VLA, abbreviated as HyVLA-0.5, an end-to-end system that spans the full robot learning stack: data collection, model design, continued pre-training and supervised fine-tuning, RL post-training, and real-world deployment. Each component serves a distinct role in this stack.

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)
• Generalization of World Models under Environmental Variability for Vision-based Quadrotor Navigation [10.364779390403337]
  World models, learned generative models that predict how an environment evolves, have become a promising tool for sample-efficient robot learning.<n>We conduct a systematic study using vision-based quadrotor navigation as a testbed problem, training DreamerV3-based world models under varying levels of environmental randomness.<n>We then deploy all world models and associated navigation policies on a real quadrotor in unseen environments, including an open-loop run where the model receives just 2.5s of real sensory input before all sensors are cut off.<n>Our results show that world model robustness during SSL pretraining is a strong predictor of sim-to-real
  arXiv  Detail & Related papers  (2026-06-03T15:38:36Z)
• DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA [72.9197085473598]
  DIAL is a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck.<n>A VLM-based System-2 performs latent world modeling by latent visual foresight within the VLM's native feature space.<n>A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions.
  arXiv  Detail & Related papers  (2026-03-31T15:02:27Z)
• GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning [44.63316677431278]
  We present textitGigaBrain-0.5M*, a VLA model trained via world model-based reinforcement learning.<n>textitGigaBrain-0.5M* is built upon textitGigaBrain-0.5, which is pre-trained on over 10,000 hours of robotic manipulation data.
  arXiv  Detail & Related papers  (2026-02-12T15:55:19Z)
• World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy [55.03832008486675]
  World-VLA-Loop is a closed-loop framework for the joint refinement of world models and Vision-Language-Action (VLA) policies.<n>We propose a state-aware video world model that functions as a high-fidelity interactive simulator by jointly predicting future observations and reward signals.
  arXiv  Detail & Related papers  (2026-02-06T08:57:55Z)
• Green-VLA: Staged Vision-Language-Action Model for Generalist Robots [0.0]
  We introduce Green-VLA, a staged Vision-Language-Action framework for real-world deployment on the Green humanoid robot.<n>We couple a scalable data-processing pipeline with temporal alignment and quality filtering, and use a unified, embodiment-aware action interface.<n>Experiments on Simpler BRIDGE WidowX and CALVIN ABC-D, as well as real-robot evaluations, show strong generalization and performance gains from RL alignment.
  arXiv  Detail & Related papers  (2026-01-31T22:13:23Z)
• Galaxea Open-World Dataset and G0 Dual-System VLA Model [55.756245350141675]
  We present a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments.<n>All demonstrations are gathered using a consistent robotic embodiment, paired with precise subtask-level language annotations.<n>G0 is trained using a three-stage curriculum: cross-embodiment pre-training, single-embodiment pre-training, and task-specific post-training.
  arXiv  Detail & Related papers  (2025-08-30T18:04:19Z)
• MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models [34.138699712315]
  This paper introduces a novel vision--action (VLA) model, mixture of robotic experts (MoRE) for quadruped robots.<n>MoRE integrates multiple low-rank adaptation modules as distinct experts within a dense multi-modal large language model.<n>Experiments demonstrate that MoRE outperforms all baselines across six different skills and exhibits superior generalization capabilities in out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-03-11T03:13:45Z)
• 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)

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.