Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Pang Wei Koh

Pang Wei Koh

Extending the WILDS Benchmark for Unsupervised Adaptation


Dec 09, 2021
Shiori Sagawa, Pang Wei Koh, Tony Lee, Irena Gao, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo, Jure Leskovec, Kate Saenko, Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang

Figure 1 for Extending the WILDS Benchmark for Unsupervised Adaptation
Figure 2 for Extending the WILDS Benchmark for Unsupervised Adaptation
Figure 3 for Extending the WILDS Benchmark for Unsupervised Adaptation
Figure 4 for Extending the WILDS Benchmark for Unsupervised Adaptation

  Access Paper or Ask Questions

On the Opportunities and Risks of Foundation Models


Aug 16, 2021
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dora Demszky, Chris Donahue, Moussa Doumbouya, Esin Durmus, Stefano Ermon, John Etchemendy, Kawin Ethayarajh, Li Fei-Fei, Chelsea Finn, Trevor Gale, Lauren Gillespie, Karan Goel, Noah Goodman, Shelby Grossman, Neel Guha, Tatsunori Hashimoto, Peter Henderson, John Hewitt, Daniel E. Ho, Jenny Hong, Kyle Hsu, Jing Huang, Thomas Icard, Saahil Jain, Dan Jurafsky, Pratyusha Kalluri, Siddharth Karamcheti, Geoff Keeling, Fereshte Khani, Omar Khattab, Pang Wei Koh, Mark Krass, Ranjay Krishna, Rohith Kuditipudi, Ananya Kumar, Faisal Ladhak, Mina Lee, Tony Lee, Jure Leskovec, Isabelle Levent, Xiang Lisa Li, Xuechen Li, Tengyu Ma, Ali Malik, Christopher D. Manning, Suvir Mirchandani, Eric Mitchell, Zanele Munyikwa, Suraj Nair, Avanika Narayan, Deepak Narayanan, Ben Newman, Allen Nie, Juan Carlos Niebles, Hamed Nilforoshan, Julian Nyarko, Giray Ogut, Laurel Orr, Isabel Papadimitriou, Joon Sung Park, Chris Piech, Eva Portelance, Christopher Potts, Aditi Raghunathan, Rob Reich, Hongyu Ren, Frieda Rong, Yusuf Roohani, Camilo Ruiz, Jack Ryan, Christopher Ré, Dorsa Sadigh, Shiori Sagawa, Keshav Santhanam, Andy Shih, Krishnan Srinivasan, Alex Tamkin, Rohan Taori, Armin W. Thomas, Florian Tramèr, Rose E. Wang, William Wang, Bohan Wu, Jiajun Wu, Yuhuai Wu, Sang Michael Xie, Michihiro Yasunaga, Jiaxuan You, Matei Zaharia, Michael Zhang, Tianyi Zhang, Xikun Zhang, Yuhui Zhang, Lucia Zheng, Kaitlyn Zhou, Percy Liang

Figure 1 for On the Opportunities and Risks of Foundation Models
Figure 2 for On the Opportunities and Risks of Foundation Models
Figure 3 for On the Opportunities and Risks of Foundation Models
Figure 4 for On the Opportunities and Risks of Foundation Models
* Published by the Center for Research on Foundation Models (https://crfm.stanford.edu/) 
  Access Paper or Ask Questions

Just Train Twice: Improving Group Robustness without Training Group Information


Jul 19, 2021
Evan Zheran Liu, Behzad Haghgoo, Annie S. Chen, Aditi Raghunathan, Pang Wei Koh, Shiori Sagawa, Percy Liang, Chelsea Finn

Figure 1 for Just Train Twice: Improving Group Robustness without Training Group Information
Figure 2 for Just Train Twice: Improving Group Robustness without Training Group Information
Figure 3 for Just Train Twice: Improving Group Robustness without Training Group Information
Figure 4 for Just Train Twice: Improving Group Robustness without Training Group Information
* International Conference on Machine Learning (ICML), 2021 
  Access Paper or Ask Questions

Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization


Jul 09, 2021
John Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, Ludwig Schmidt

Figure 1 for Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
Figure 2 for Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
Figure 3 for Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
Figure 4 for Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization

  Access Paper or Ask Questions

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


Dec 14, 2020
Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang

Figure 1 for WILDS: A Benchmark of in-the-Wild Distribution Shifts
Figure 2 for WILDS: A Benchmark of in-the-Wild Distribution Shifts
Figure 3 for WILDS: A Benchmark of in-the-Wild Distribution Shifts
Figure 4 for WILDS: A Benchmark of in-the-Wild Distribution Shifts

  Access Paper or Ask Questions

Selective Classification Can Magnify Disparities Across Groups


Oct 27, 2020
Erik Jones, Shiori Sagawa, Pang Wei Koh, Ananya Kumar, Percy Liang

Figure 1 for Selective Classification Can Magnify Disparities Across Groups
Figure 2 for Selective Classification Can Magnify Disparities Across Groups
Figure 3 for Selective Classification Can Magnify Disparities Across Groups
Figure 4 for Selective Classification Can Magnify Disparities Across Groups

  Access Paper or Ask Questions

Concept Bottleneck Models


Jul 09, 2020
Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang

Figure 1 for Concept Bottleneck Models
Figure 2 for Concept Bottleneck Models
Figure 3 for Concept Bottleneck Models
Figure 4 for Concept Bottleneck Models
* ICML 2020 
  Access Paper or Ask Questions

An Investigation of Why Overparameterization Exacerbates Spurious Correlations


May 09, 2020
Shiori Sagawa, Aditi Raghunathan, Pang Wei Koh, Percy Liang

Figure 1 for An Investigation of Why Overparameterization Exacerbates Spurious Correlations
Figure 2 for An Investigation of Why Overparameterization Exacerbates Spurious Correlations
Figure 3 for An Investigation of Why Overparameterization Exacerbates Spurious Correlations
Figure 4 for An Investigation of Why Overparameterization Exacerbates Spurious Correlations

  Access Paper or Ask Questions

ExpBERT: Representation Engineering with Natural Language Explanations


May 05, 2020
Shikhar Murty, Pang Wei Koh, Percy Liang

Figure 1 for ExpBERT: Representation Engineering with Natural Language Explanations
Figure 2 for ExpBERT: Representation Engineering with Natural Language Explanations
Figure 3 for ExpBERT: Representation Engineering with Natural Language Explanations
Figure 4 for ExpBERT: Representation Engineering with Natural Language Explanations
* ACL 2020 
  Access Paper or Ask Questions

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization


Nov 20, 2019
Shiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, Percy Liang

Figure 1 for Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
Figure 2 for Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
Figure 3 for Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
Figure 4 for Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

  Access Paper or Ask Questions

Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations


Sep 14, 2019
Sawyer Birnbaum, Volodymyr Kuleshov, Zayd Enam, Pang Wei Koh, Stefano Ermon

Figure 1 for Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations
Figure 2 for Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations
Figure 3 for Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations
Figure 4 for Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations
* Accepted to NeurIPS 2019 
  Access Paper or Ask Questions

On the Accuracy of Influence Functions for Measuring Group Effects


May 30, 2019
Pang Wei Koh, Kai-Siang Ang, Hubert H. K. Teo, Percy Liang

Figure 1 for On the Accuracy of Influence Functions for Measuring Group Effects
Figure 2 for On the Accuracy of Influence Functions for Measuring Group Effects
Figure 3 for On the Accuracy of Influence Functions for Measuring Group Effects
Figure 4 for On the Accuracy of Influence Functions for Measuring Group Effects

  Access Paper or Ask Questions

Stronger Data Poisoning Attacks Break Data Sanitization Defenses


Nov 02, 2018
Pang Wei Koh, Jacob Steinhardt, Percy Liang

Figure 1 for Stronger Data Poisoning Attacks Break Data Sanitization Defenses
Figure 2 for Stronger Data Poisoning Attacks Break Data Sanitization Defenses
Figure 3 for Stronger Data Poisoning Attacks Break Data Sanitization Defenses
Figure 4 for Stronger Data Poisoning Attacks Break Data Sanitization Defenses

  Access Paper or Ask Questions

Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data


Jul 12, 2018
Emma Pierson, Pang Wei Koh, Tatsunori Hashimoto, Daphne Koller, Jure Leskovec, Nicholas Eriksson, Percy Liang

Figure 1 for Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data
Figure 2 for Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data
Figure 3 for Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data
Figure 4 for Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data
* Accepted at Joint ICML and IJCAI Workshop on Computational Biology, 2018 
  Access Paper or Ask Questions

Certified Defenses for Data Poisoning Attacks


Nov 24, 2017
Jacob Steinhardt, Pang Wei Koh, Percy Liang

Figure 1 for Certified Defenses for Data Poisoning Attacks
Figure 2 for Certified Defenses for Data Poisoning Attacks
Figure 3 for Certified Defenses for Data Poisoning Attacks
Figure 4 for Certified Defenses for Data Poisoning Attacks
* Appeared at NIPS 2017 
  Access Paper or Ask Questions

Understanding Black-box Predictions via Influence Functions


Jul 10, 2017
Pang Wei Koh, Percy Liang

Figure 1 for Understanding Black-box Predictions via Influence Functions
Figure 2 for Understanding Black-box Predictions via Influence Functions
Figure 3 for Understanding Black-box Predictions via Influence Functions
Figure 4 for Understanding Black-box Predictions via Influence Functions
* International Conference on Machine Learning, 2017 
  Access Paper or Ask Questions