RadarAI· X：自变量 X Square (@XSquareRobot)·· 3 小时前AI 评分38
X Square 宣布 WALL-OSS 0.5 加入 LeRobot VLA 家族
AI 导读
X Square Robot 宣布 WALL-OSS 0.5 已加入 LeRobot VLA 家族。该模型是一个 4B VLA，同时能生成文本，支持 /vqa 并自行规划子任务。LeRobot 0.7 共新增五个 VLA，其余包括 Galaxea Dynamics 的 G0.5、LingBot-VLA 2.0、Dexmal 的 DM0.5 与 FineART-VLA。
正文 · 原文
X Square Robot· @XSquareRobot · X·2026-11-12 22:17· 3 分钟前AI 评分54
AI 导读
X Square Robot 宣布 WALL-OSS 0.5 现已加入 LeRobot VLA 家族。据引用的 LeRobot 内容，WALL-OSS 0.5 是一个 4B VLA，还能生成文本，支持 /vqa 并自行规划子任务；LeRobot 0.7 共新增五个 VLA。
正文 · 原文
WALL-OSS 0.5 is now part of the LeRobot VLA family.
Great to see the ecosystem continue to grow.
在 X 查看被引用的帖子Five new VLAs in LeRobot 0.7. The zoo keeps growing 🤖
- G0.5 from @GalaxeaDynamics: a 2B VLA that writes its subtask, then its actions, in one stream. Works with /subtask and /autosteer
- LingBot-VLA 2.0 from @robbyant_brain: one model across embodiments (55-D action space, ~60,000 h of pretraining). Its sparse MoE runs an action chunk in 120 ms in LeRobot, down from 756 ms
- DM0.5 from @Dexmal_AI: a Gemma3-4B VLM + a 680M flow-matching action expert, on standard LeRobot datasets
- Wall-OSS 0.5 from @XSquareRobot: a 4B VLA that also writes text. It answers /vqa and plans its own subtasks
- FineART-VLA: π0.5 with a language head, trained on FineART (more in our language post)
Docs in the comments 👇
来源：X Square Robot · x.com
来源：RadarAI · aihot.news