Kimi k1.5: Scaling Reinforcement Learning with LLMs

Jingren Zhou is Chief Technology Officer of Alibaba Cloud. Public speaker biographies describe him as a computer scientist and entrepreneur whose work includes large-scale AI and cloud systems.

AI researcher at DeepSeek working on natural language processing, code intelligence, and large language model reasoning.

Ph.D. candidate in computer science at Princeton University working on LLM agents and machine learning. He is a coauthor of Moonshot AI's Kimi k1.5 report.

Applied research scientist at Moonshot AI Labs working on large language model reasoning and multimodal systems.

Aimin Yang is a Moonshot AI contributor and co-author of Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Xixuan Song is a Moonshot AI contributor and co-author of Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Xiao Wang is a Moonshot AI contributor and co-author of Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Mingxiao Li is a machine learning researcher focused on vision-language models, generative models, and multimodal learning. His public homepage lists a PhD at KU Leuven, and public research outputs also list him with Moonshot AI Ltd. affiliation.

Researcher at Moonshot AI focused on reinforcement learning and robotics. He earned a Ph.D. in robotics and machine learning from Carnegie Mellon University.

Public report authorship links Jie Zhou to the MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention at MiniMax.

Yingtao Zhang is a Moonshot AI contributor and co-author of Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Canonical link

Jingren Zhou

Daya Guo

Yuxi Xie

Yutao Zhou

Aimin Yang

Xixuan Song

Xiao Wang

Mingxiao Li

Fangzhou Su

Jie Zhou

Yingtao Zhang