Su Jianlin
Jianlin Su is a researcher at Moonshot AI (Kimi) known for inventing Rotary Position Embedding (RoPE), a widely adopted position encoding method for transformer models. He is listed as a contributor to the Kimi K3 model and the Kimi Linear attention architecture. His work on RoPE has been influential across the large language model community and is used in numerous open-source and production models.
“Su Jianlin, building on DeltaNet, developed how to convert DeltaNet into a GPU-computable Chunk Recurrent computation pattern.”
Source→“RoPE was originally proposed by Su Jianlin, which I find quite interesting. Just as in the V4 discussion, V4 ended up not using MLA — these are significant contributions to the industry. And Su Jianlin is also a very core researcher at Kimi.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.