·
Founder & CEO |Moonshot AI
Author of Transformer-XL and XLNet papers. CMU doctorate, ex-Meta/Google Brain. Created Kimi chatbot and led breakthroughs in long-context LLM attention and optimizer scaling.
GitHub
9 repositories · 5.2k total stars
Semi-supervised learning with graph embeddings
Good Semi-Supervised Learning That Requires a Bad GAN
Review Network for Caption Generation
Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
Unsupervised Learning of Transferable Relational Graphs
Fine-grained Gating for Reading Comprehension
Multi-modal Bayesian embedding model
Languages
Episodes