Vincent Sunn Chen

Leading ML Engineering at Snorkel AI, where we're building the data-first platform for AI application development — join us!

In my graduate work at the Stanford AI Lab, I worked with Chris Ré and members of Hazy Research to build multi-task/weak supervision systems in Snorkel. I focused on the long-tail challenges supervising and monitoring critical data slices, in domains like computer vision and healthcare.
In the past, I worked on the data engine for Tesla's Autopilot and ML interfaces for fighting fraud at Sift Science.
At Stanford, I had the pleasure co-directing TreeHacks, the university's flagship hackathon.

Here's an incomplete list of my reading, writing, and photography.

Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

Vincent S Chen, Zhenzhen Weng, Alexander Ratner, Christopher Ré

In NeurIPS 2019. [blog] [slides] [paper] [code]

Scene Graph Prediction with Limited Labels

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

In ICCV 2019. [paper] [code] [poster]

Powerful Abstractions for Programming Your Training Data

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

SuperGLUE Benchmark. [blog] [code]

Massive Multi-Task Learning: 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

GLUE Benchmark. [blog]

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

In Nature Communications 2019. [paper] [code]

Automated Training Set Generation for Aortic Valve Classification

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

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

In NeurIPS 2017, ML4H Workshop. [poster]

vincent sunn chen

projects