Machine learning researcher working on efficient systems for large models. PhD at Princeton with Kai Li and Jason D. Lee, after Peking University with Liwei Wang and Di He; earlier a part-time researcher at Together AI with Tri Dao, and a researcher at Google DeepMind and Microsoft Research. First author of Large Language Models as Tool Makers and first-listed author of Medusa, which speeds up inference with extra decoding heads.
Path
Princeton UniversityPhD, advised by Kai Li and Jason D. Lee
Together AIPart-time researcher, with Tri Dao
Google DeepMindResearcher, with Xuezhi Wang and Denny Zhou
Microsoft ResearchResearcher, with Sébastien Bubeck and Debadeepta Dey
Sourcesx.comtianle.websitearxiv.orgarxiv.org/2401.10774Education and jobs are read from their own homepage or employer's page; papers checked on arXiv. From LinkedIn only the person's own public posts are read; GitHub is a link only.
Account links back to x.com/tianle_cai · Avatar from their X account, taken 2026-11-03
Nothing else on the record names them yet.
Something wrong or missing on this page? Tell me and it will be fixed or removed. Contact →