Sotabase

Career

· Assistant Professor, Stanford University2018–
· Research Scientist, Facebook2017–2018
· Visiting Researcher, Facebook AI Research2017–
· PhD student, Computer Science, Princeton University2012–2017
· Undergraduate Studies, Tsinghua University

Publications (1386)

On the Opportunities and Risks of Foundation Models
arXiv.org · 2021
5,795
cited
SAM 2: Segment Anything in Images and Videos
International Conference on Learning Representations · 2024
2,350
cited
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Neural Information Processing Systems · 2019
1,924
cited
A Simple but Tough-to-Beat Baseline for Sentence Embeddings
International Conference on Learning Representations · 2017
1,382
cited
An Explanation of In-context Learning as Implicit Bayesian Inference
International Conference on Learning Representations · 2021
950
cited
MOPO: Model-based Offline Policy Optimization
Neural Information Processing Systems · 2020
872
cited
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
International Conference on Learning Representations · 2022
843
cited
Generalization and Equilibrium in Generative Adversarial Nets (GANs)
International Conference on Machine Learning · 2017
712
cited
What learning algorithm is in-context learning? Investigations with linear models
International Conference on Learning Representations · 2022
630
cited
Matrix Completion has No Spurious Local Minimum
Neural Information Processing Systems · 2016
619
cited
Identity Matters in Deep Learning
International Conference on Learning Representations · 2016
408
cited
Verified Uncertainty Calibration
Neural Information Processing Systems · 2019
407
cited
Why is nonvolatile ferroelectric memory field-effect transistor still elusive?
IEEE Electron Device Letters · 2002
406
cited
A Latent Variable Model Approach to PMI-based Word Embeddings
Transactions of the Association for Computational Linguistics · 2015
380
cited
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss
Neural Information Processing Systems · 2021
374
cited
Fixup Initialization: Residual Learning Without Normalization
International Conference on Learning Representations · 2019
371
cited
Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling
AAAI Conference on Artificial Intelligence · 2020
341
cited
Provable Bounds for Learning Some Deep Representations
International Conference on Machine Learning · 2013
338
cited
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
Neural Information Processing Systems · 2019
328
cited
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations
Annual Conference Computational Learning Theory · 2017
317
cited
Sotabase