Weijie Su

We're hiring a postdoc focused on the statistical foundations of large language models, starting this fall. Join our team exploring the theoretical and statistical underpinnings of LLMs. If interested, check our work: weijie-su.com/llm/ and drop me an email. #AIResearch…

Holy shit. Kimi K2 was pre-trained on 15.5T tokens using MuonClip with zero training spike. Muon has officially scaled to the 1-trillion-parameter LLM level. Many doubted it could scale, but here we are. So proud of the Moum team: @kellerjordan0, @bozavlado, @YouJiacheng,…

As AI models become more humanlike, traditional detection tools are falling behind. A study from @weijie444, @DrQiLong & more introduces a framework to evaluate and strengthen watermarking methods, making them more resilient to edits and easier to detect: whr.tn/441Bbd3

I just wrote a position paper on the relation between statistics and large language models: Do Large Language Models (Really) Need Statistical Foundations? arxiv.org/abs/2505.19145 Any comments are welcome. Thx

Congratulations to the 2025 Class of IMS Fellows! Each Fellow has demonstrated distinction in research in statistics or probability or has demonstrated leadership that has profoundly influenced the field. See the new Fellows here: imstat.org/2025/05/05/con…