Vincent Sunn Chen

I'm a graduate student at Stanford with a concentration in machine learning and a minor in creative writing. I'm interested in shaping datasets to make deep learning more accesible to domain experts in fields like medical imaging.

I'm currently a research assistant in the Stanford AI Lab with Chris Ré, building multi-task/weak supervision systems in Snorkel.
Most recently, I worked on the data engine for training neural networks on Autopilot vision team at Tesla.
In the past, I worked at Sift Science to fight fraud with machine learning, Xbox to build virtual reality experiences, and EMGuidance to build point-of-care healthcare tools.
At Stanford, I had a lot of fun co-directing TreeHacks, the university's flagship hackathon.

I also love reading, writing, and photography!

Scene Graph Prediction with Limited Labels

Vincent S Chen, Paroma Varma, Ranjay Krishna, Michael Bernstein, Christopher Re, Li Fei-Fei

ICCV 2019.

Powerful Abstractions for Programming Your Training Data

Sen Wu, Vincent S. Chen, Braden Hancock, ALex Ratner, Chris Ré, and other members of Hazy Lab

Blog [SuperGLUE 1.9 state-of-the-art, 06/15/2019]

Massive Multi-Task Learning with Snorkel: Bringing More Supervision to Bear

Braden Hancock, Clara McCreery, Ines Chami, Vincent S. Chen, Sen Wu, Jared Dunnmon, Paroma Varma, Max Lam, and Chris Ré

Blog [GLUE state-of-the-art, 03/22/2019]

Weakly supervised classification of rare aortic valve malformations using unlabeled cardiac MRI sequences

Jason A Fries, Paroma Varma, Vincent S Chen, Ke Xiao, Heliodoro Tejeda, Priyanka Saha, Jared Dunnmon, Henry Chubb, Shiraz Maskatia, Madalina Fiterau, Scott Delp, Euan Ashley, Christopher Ré, James Priest

Nature Communications.

Automated Training Set Generation for Aortic Valve Classification

Vincent Chen, Paroma Varma, Madalina Fiterau, James Priest and Christopher Ré.

NeurIPS 2017, ML4H Workshop.

Using weak-supervision, we learn probabilistic training labels for aortic valve MRIs.

vincent sunn chen

projects

Scene Graph Prediction with Limited Labels

Powerful Abstractions for Programming Your Training Data

Massive Multi-Task Learning with Snorkel: Bringing More Supervision to Bear

Weakly supervised classification of rare aortic valve malformations using unlabeled cardiac MRI sequences

Automated Training Set Generation for Aortic Valve Classification

teaching

CS231N: Convolutional Neural Networks for Visual Recognition