Hy-Embodied-0.5-VLA — LeRobot Conversion
lerobot/hy_vla_robotwin
LeRobot has released a converted version of the Hy-Embodied-0.5-VLA-RoboTwin model, achieving full forward parity with the original model. The model supports a 16D dual-arm embodiment and has been validated across multiple metrics, including task completion and action accuracy. The release highlights the model's performance on a RoboTwin quick protocol and notes limitations in expressing mobile-manipulator actions.
Full article
You are reading the complete RoboSignal summary. The publisher’s full article is available at the original source.
Read full article at sourcehuggingface.co · Opens in a new tab; source language may differ.
The release details a model conversion and validation process for a robotic policy, showing full parity between the original and converted model across various metrics. The model supports a specific 16D dual-arm embodiment and has limitations in expressing mobile-manipulator actions.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- dataset: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
Hy-Embodied-0.5-VLA — LeRobot conversion Byte-identical tensor conversion of tencent/Hy-Embodied-0.5-VLA-RoboTwin at revision bd7bba6f5934ad62293a2a34f74760c6a3ef2ff8 .
Open source E1
Model token horizon: 40 Physical action horizon: 20 Actions executed per sample: 7 Image history: 6 frames at interval 5 Action representation: relative_absolute Euler inference steps: 10
Open source E2
Validation Strict load, save_pretrained , and strict reload passed with all 1,628 tensors mapped and no missing, unexpected, duplicate, or shape-mismatched tensors.
Open source E3
On the pinned first-six-task RoboTwin quick protocol, the author wrapper scored 60/60. LeRobot scored 53/54 completed episodes; conservatively counting one native-planner hang as a failure gives 53/55 (96.36%) versus the matched author subset's 55/55, a 3.64-percentage-point delta.
Open source E4
Limitation This policy supports the released 16D dual-arm pose/gripper embodiment only. A 12D mobile-manipulator action contains base semantics that the released 20D dual-arm representation cannot express and is rejected rather than silently truncated or reinterpreted.
Open source E5
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：LeRobot — Model repository updates · huggingface.co