Kimi Linear: An Expressive, Efficient Attention Architecture
Kimi K2: Open Agentic Intelligence
Kimi-VL Technical Report
Muon is Scalable For LLM Training
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
Automatic Truss Design with Reinforcement Learning
NLP From Scratch Without Large-Scale Pre-training: A Simple and Efficient Framework
SimCSE: Simple Contrastive Learning of Sentence Embeddings
Research Experience
Currently an AI researcher at Moonshot AI, involved in multiple research projects including Kimi Linear, Kimi K2, etc.
Education
Received his Bachelor’s degree from IIIS (Yao Class), Tsinghua University, where he had the opportunity to work with Prof. Danqi Chen and Prof. Zhilin Yang.
Background
An AI researcher currently working at Moonshot AI, developing KimiChat. He was planning to pursue a PhD at UCLA under the advisement of Prof. Kai-Wei Chang but decided to postpone this plan as he got AGI-pilled. He is excited to contribute to the development of artificial general intelligence and explore its potential impact on humanity.