Kendrick Shen

I am currently a machine learning research engineer at Genesis Therapeutics. I graduated from Stanford in June '22 studying computer science (M.S., B.S. with honors) and keyboard music (B.A. with honors). While at Stanford, I worked with Professors Tengyu Ma and Percy Liang at the Stanford AI Lab and with Dr. Sharon Hori at the Canary Center for Cancer Early Detection. I love playing the classical piano and guitar and enjoy learning about music composition, analysis, history, and theory.

Research (* denotes equal contribution)

Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
Kendrick Shen*, Robbie Jones*, Ananya Kumar*, Sang Michael Xie*, Jeff Z. HaoChen, Tengyu Ma, and Percy Liang
International Conference on Machine Learning (ICML), 2022
Long presentation (2.1% of submissions)

Extending the WILDS Benchmark for Unsupervised Adaptation
Shiori Sagawa*, Pang Wei Koh*, Tony Lee*, Irena Gao*, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo, Jure Leskovec, Kate Saenko, Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, and Percy Liang
International Conference on Learning Representations (ICLR), 2022
Oral presentation (1.6% of submissions)

Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Colin Wei, Kendrick Shen, Yining Chen, and Tengyu Ma
International Conference on Learning Representations (ICLR), 2021
Oral presentation (1.8% of submissions)