Sang Michael Xie

发表

WILDS: A Benchmark of in-the-Wild Distribution Shifts pdf

Jure Leskovec, Sergey Levine, Chelsea Finn, 2020, ArXiv.

Reparameterizable Subset Sampling via Continuous Relaxations

Stefano Ermon, Sang Michael Xie, S. Ermon, 2019, IJCAI.

Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance

Stefano Ermon, Sang Michael Xie, Neal Jean, 2018, NeurIPS.

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness pdf

Tengyu Ma, Fereshte Khani, Percy Liang, 2020, ICLR.

Differentiable Subset Sampling pdf

Stefano Ermon, Sang Michael Xie, 2019, ArXiv.

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy pdf

John Duchi, Aditi Raghunathan, Fanny Yang, 2020, ICML.

Adversarial Training Can Hurt Generalization pdf

Aditi Raghunathan, Percy Liang, John C. Duchi, 2019, ArXiv.

Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping

Stefano Ermon, David B. Lobell, Sang Michael Xie, 2015, AAAI.

Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization pdf

Tengyu Ma, Percy Liang, Sang Michael Xie, 2020, ICML.

Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery

David B. Lobell, Sang Michael Xie, Sherrie Wang, 2020, Remote. Sens..

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness pdf

Sang Michael Xie, Tengyu Ma, Ananya Kumar, 2021, ICLR 2021 Poster.

WILDS: A Benchmark of in-the-Wild Distribution Shifts

Jure Leskovec, Sergey Levine, Chelsea Finn, 2021, ICML.

Combining satellite imagery and machine learning to predict poverty

Sang Michael Xie, S. Ermon, D. Lobell, 2016, Science.

Semi-supervised deep kernel learning

Stefano Ermon, Sang Michael Xie, Neal Jean, 2016 .

MAPPING POVERTY WITH SATELLITE IMAGERY A THESIS SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF BACHELORS OF SCIENCE WITH HONORS

Sang Michael Xie, 2017 .

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy pdf

John Duchi, Aditi Raghunathan, Percy Liang, 2020, ICML.

An Explanation of In-context Learning as Implicit Bayesian Inference

Sang Michael Xie, Percy Liang, Aditi Raghunathan, 2021, ArXiv.

An Explanation of In-context Learning as Implicit Bayesian Inference

Sang Michael Xie, Percy Liang, Aditi Raghunathan, 2021, ICLR.

On the Opportunities and Risks of Foundation Models

Michael S. Bernstein, Juan Carlos Niebles, Christopher D. Manning, 2021, ArXiv.

Automated detection of skin reactions in epicutaneous patch testing using machine learning

Sang Michael Xie, K. Sarin, G. Honari, 2021, The British journal of dermatology.

WILDS: A Benchmark of in-the-Wild Distribution Shifts

Pang Wei Koh, Sang Michael Xie, Berton A. Earnshaw, 2020, ICML.

2022 Source Labeled Unlabeled Belgium France Norway Validation China Target United States Canada UK Japan Mexico Extra

Pang Wei Koh, Sang Michael Xie, Ananya Kumar, 2022 .

No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets pdf

Percy Liang, Sang Michael Xie, Fahim Tajwar, 2021, ArXiv.

Holistic Evaluation of Language Models

Christopher D. Manning, Sang Michael Xie, Niladri S. Chatterji, 2023, Annals of the New York Academy of Sciences.

Reward Design with Language Models

Sang Michael Xie, Sang Michael Xie, Minae Kwon, 2023, ICLR.

DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining

Sang Michael Xie, Sang Michael Xie, Quoc V. Le, 2023, ArXiv.

Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models

Sang Michael Xie, Sang Michael Xie, Zhiyuan Li, 2022, ICML.

Data Selection for Language Models via Importance Resampling

Sang Michael Xie, Sang Michael Xie, Percy Liang, 2023, ArXiv.

Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation

Sang Michael Xie, Jeff Z. HaoChen, Sang Michael Xie, 2022, ICML.

Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation

Sang Michael Xie, Jeff Z. HaoChen, Sang Michael Xie, 2022, International Conference on Machine Learning.

Data Selection for Language Models via Importance Resampling

Sang Michael Xie, Percy Liang, Shibani Santurkar, 2023, ArXiv.

Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning

Sang Michael Xie, Sang Michael Xie, Colin Wei, 2021, NeurIPS.

Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization

Sang Michael Xie, Percy Liang, Tengyu Ma, 2020, ICML.

Holistic Evaluation of Language Models

Christopher D. Manning, Sang Michael Xie, Niladri S. Chatterji, 2023, Trans. Mach. Learn. Res..

DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining

Adams Wei Yu, Sang Michael Xie, Quoc V. Le, 2023, NeurIPS.

On the Opportunities and Risks of Foundation Models

Michael S. Bernstein, Juan Carlos Niebles, Christopher D. Manning, 2021, ArXiv.