Steven Cao

Google Scholar | CV
shcao [at] stanford.edu



Hi! I am a PhD student at Stanford, where I am grateful to be advised by Percy Liang and Gregory Valiant. My research is in language modeling, machine learning, and theory. Recently, I've been thinking about fundamental questions in pretraining, especially around scaling and data efficiency.


Recent Publications


Selected Publications


On the Entropy Calibration of Language Models Steven Cao, Gregory Valiant, Percy Liang NeurIPS, 2025

One-sided Matrix Completion from Two Observations Per Row Steven Cao, Percy Liang, Gregory Valiant ICML, 2023

Low Complexity Probing via Finding Subnetworks Steven Cao, Victor Sanh, Alexander M. Rush NAACL, 2021

Unsupervised Parsing via Constituency Tests Steven Cao, Nikita Kitaev, Dan Klein EMNLP, 2020

Multilingual Alignment of Contextual Word Representations Steven Cao, Nikita Kitaev, Dan Klein ICLR, 2020


Personal


My friend is writing a cool newsletter discussing new releases in Chinese literature! You can find it here.