Xiaomi's MiMo-V2.6 Likely the Largest Single RL Run by an Open-Source Team, Now Top Open Model
timshi_ai · x · 2026-09-22
Luo Fuli detailed MiMo-V2.6: by compute, likely the largest single RL run any open-source model team has undertaken, with a dozens-strong team focused solely on scaling up RL. The model's potential was built via mid-training and unlocked through heavy RL, and it now ranks as the number one open-source model.
- Commenters note the 31-year-old lead runs Xiaomi's most important initiative, calling it proof of meritocratic culture in Chinese tech.
- A Peking University profile adds she came from an ordinary small-city upbringing, rejects the "genius" label, and asked to be left alone to "work on difficult and right things in peace."
More from Companies & People
- KubeCon keynote: computing is shifting from human speed to agent speed — HowDevelop · 2026-11-12
- Leaked memo: Meta infrastructure head Santosh Janardhan to leave in early 2027 — dinabass · 2026-11-12
- Epic AI MegaJam finals in SF Nov 14-15: teams of 4 plus unlimited AI agents — chrisfirst · 2026-11-12
- VulnCheck audit: Anthropic's Project Glasswing logged 37,966 findings, only 217 fixed — GaryMarcus · 2026-11-12
- YC-backed Monte launches post-training platform to build proprietary models from your agents' real work — ycombinator · 2026-11-12
- Investor: AI diffusion will be slowest in consumer software — Oura, Strava, Labcorp still have no real AI strategy — MartinGTobias · 2026-11-12