AnalysisAI ModelsSeptember 18, 2026

Xiaomi livestreams MiMo-V2.6 reinforcement-learning training

Read original source →technode.com

Xiaomi's MiMo team is publicly streaming RL training of unreleased MiMo-V2.6-Pro and MiMo-V2.6-Flash via a dashboard showing reward curves, rollout counts, step timing and running compute costs. MiMo head Luo Fuli said the team spent nearly six months studying how far RL could scale after MiMo-V2.5.

People · Luo Fuli

How this story unfolded

2 days · 1 report · 2 community posts · from Sep 16

  1. Sep 16
  2. Sep 18

More stories today

Open the live feed