Industry
xiaomi MiMo oss RL environments + training code https://github.com/XiaomiMiMo/verl https://huggingface.co/datasets/XiaomiMiMo/MiMo-V2.6-RL-o…
Xiaomi has released an open‑source reinforcement‑learning framework called MiMo (version V2.6) that bundles a suite of simulated environments together with training scripts. The code is hosted on GitH
Xiaomi has released an open‑source reinforcement‑learning framework called MiMo (version V2.6) that bundles a suite of simulated environments together with training scripts. The code is hosted on GitHub at https://github.com/XiaomiMiMo/verl, while the associated dataset can be downloaded from Hugging Face under the name XiaomiMiMo/MiMo-V2.6-RL-oss. These resources provide a standardized environment set and benchmark data for RL research.
Related
- emmmm 一直以为训练 RL 这一块语料会很大 看起来是我不了解了 比我预期的低了好几个数量级 anyway 感谢一下公开学习材料
- incredibly based that Xiaomi MiMo released their RL dataset link: https://huggingface.co/datasets/XiaomiMiMo/MiMo-V2.6-RL-oss
Source: Clem Delangue (X) | 2026-09-26