moonshot-ai

llm ,  paper ,  open-weights ,  moe ,  technical-report ,  agent ,  moonshot-ai ,  kimi-k3

mixture-of-experts ,  long-context ,  moba ,  moonshot-ai ,  moonshotai ,  block-attention ,  sparse-attention ,  mixture-of-block-attention

llm ,  open-weights ,  moe ,  agent ,  kimi ,  moonshot-ai ,  kimi-k3

moonshot-ai ,  mcp ,  terminal ,  cli ,  coding-agent ,  kimi-code

early-fusion ,  moonshot-ai ,  kimi-k2-5 ,  agent-swarm ,  general-agentic-intelligence ,  multimodal-model ,  dip-and-recover ,  zero-vision-supervised-fine-tuning ,  joint-multimodal-rl ,  parallel-agent-reinforcement-learning ,  decoupled-encoder-process

moe ,  task-automation ,  kimi-k2 ,  moonshot-ai ,  agentic-llm ,  muonclip-optimizer ,  agentic-capabilities ,  general-reinforcement-learning