Kimi-K2 Collection Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 2 items • Updated 19 days ago • 113
🐙 OctoThinker Collection Mid-training Incentivizes Reinforcement Learning Scaling • 18 items • Updated Jun 26 • 2
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling Paper • 2506.20512 • Published Jun 25 • 46