AIBase
Home
AI NEWS
AI Tools
GEO & AEO
MCP
AI Models
Join Now
EN

AI News

View More

Xiaomi Publicly Reveals the RL Training Process of MiMo-V2.6 Large Model, Luofuli Posts to Confirm Open-Sourcing Technical Details

On Sept 17, Xiaomi MiMo team lead Luo Fuli first revealed MiMo-V2.6 reinforcement learning progress and livestreamed the RL stage. This marks a breakthrough in physical-world and general intelligence; technical details will be open-sourced in weeks. The model is undergoing large-scale multi-task agent training.....

17.2k 3 minutes ago
Xiaomi Publicly Reveals the RL Training Process of MiMo-V2.6 Large Model, Luofuli Posts to Confirm Open-Sourcing Technical Details

Burns Three Hundred Thousand Dollars Per Hour! Luofuli, a Former DeepSeek Expert, Makes Her First Live Stream on Large Model Training After Joining Xiaomi

Xiaomi MiMo lead and ex-DeepSeek researcher Luo Fuli returned after six months, livestreaming LLM training on X on Sept 17, marking her return to tech competition and offering a first look at Xiaomi's next-gen model training. MiMo-V2.6 is in RL experiments with three scaling directions planned.....

14.2k 1 hours ago
Burns Three Hundred Thousand Dollars Per Hour! Luofuli, a Former DeepSeek Expert, Makes Her First Live Stream on Large Model Training After Joining Xiaomi
AIBase
Empowering the future, your artificial intelligence solution think tank
English简体中文繁體中文にほんご
FirendLinks:
AI Newsletters AI ToolsMCP ServersAI NewsAI MarketingLLM LeaderboardAI Ranking
© 2026AIBase
Business CooperationSite Map