Vincent Sunn Chen

writing

Benchmarks should shape the frontier, not just measure it · Apr 2026
Closing the Evaluation Gap in Agentic AI · Feb 2026
Design Principles for Iteratively Building AI Applications · Nov 2021
Powerful Abstractions for Programmatically Building and Managing Training Sets (Stanford AI Lab blog) · Jun 2019
Learning Math for Machine Learning · Aug 2018
Building for the Blockchain (with Ramon Recuero) · Jan 2018
How to Get into VR · May 2017
How To Get Into Natural Language Processing · Jan 2017

publications

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong, et al. (36 authors, incl. Vincent Sunn Chen)

arXiv 2026 · paper

Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments

Parth Asawa, Christopher M. Glaze, Gabriel Orlanski, Ramya Ramakrishnan, Benji Xu, Asim Biswal, Vincent Sunn Chen, Frederic Sala, Matei Zaharia, Joseph E. Gonzalez

arXiv 2026 · paper

Agents’ Last Exam

Yiyou Sun, Xinyang Han, Weichen Zhang, et al. (310+ authors, incl. Vincent Sunn Chen)

arXiv 2026 · paper

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

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

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

ICCV 2019 · paper · code · poster

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 2019 · paper · code

Full list on Google Scholar.

teaching

CS231N: Convolutional Neural Networks for Visual Recognition

Teaching Assistant, Spring 2018

Hosted office hours, advised student projects, and led discussion sections on backpropagation and weak supervision.