Zongming Qiao
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
Who they are
Roles and parties from Wikidata and from the sources in the Base, as precise as each gives them. When we compare what groups say, each statement counts in the group the person belonged to that day.
- Researcher (Xiaomi LLM-Core Team), Xiaomisource
In the Base
Every entry they appear in.
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
According to the abstract, this technical report introduces the MiMo-V2.6 series, an omni-modal model family, and describes scaling reinforcement learning compute towards self-improvement; the excerpt is cut off before the results.