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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Learning Adaptive Language Interfaces through Decomposition

Oct 11, 2020
Siddharth Karamcheti, Dorsa Sadigh, Percy Liang

* Accepted at the 1st Workshop for Interactive and Executable Semantic Parsing (IntEx-SemPar) @ EMNLP 2020. 11 pages, 5 figures 

  Access Paper or Ask Questions

On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks

Oct 10, 2020
Stephen Mussmann, Robin Jia, Percy Liang

* In Findings of EMNLP 2020 

  Access Paper or Ask Questions

Task-Oriented Dialogue as Dataflow Synthesis

Oct 02, 2020
Semantic Machines, Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov

* TACL 2020 

  Access Paper or Ask Questions

Robustness to Spurious Correlations via Human Annotations

Aug 13, 2020
Megha Srivastava, Tatsunori Hashimoto, Percy Liang

* ICML 2020 final version, 16 pages, 9 figures 

  Access Paper or Ask Questions

Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning

Aug 06, 2020
Evan Zheran Liu, Aditi Raghunathan, Percy Liang, Chelsea Finn

* Project web page at https://ezliu.github.io/dream 

  Access Paper or Ask Questions

Learning Abstract Models for Strategic Exploration and Fast Reward Transfer

Jul 12, 2020
Evan Zheran Liu, Ramtin Keramati, Sudarshan Seshadri, Kelvin Guu, Panupong Pasupat, Emma Brunskill, Percy Liang


  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

* ICML 2020 

  Access Paper or Ask Questions

Simplifying Models with Unlabeled Output Data

Jun 29, 2020
Sang Michael Xie, Tengyu Ma, Percy Liang


  Access Paper or Ask Questions

Selective Question Answering under Domain Shift

Jun 16, 2020
Amita Kamath, Robin Jia, Percy Liang

* ACL 2020 

  Access Paper or Ask Questions

Graph-based, Self-Supervised Program Repair from Diagnostic Feedback

May 20, 2020
Michihiro Yasunaga, Percy Liang


  Access Paper or Ask Questions

Enabling Language Models to Fill in the Blanks

May 11, 2020
Chris Donahue, Mina Lee, Percy Liang

* To appear in the proceedings of ACL 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


  Access Paper or Ask Questions

ExpBERT: Representation Engineering with Natural Language Explanations

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

* ACL 2020 

  Access Paper or Ask Questions

Robust Encodings: A Framework for Combating Adversarial Typos

May 04, 2020
Erik Jones, Robin Jia, Aditi Raghunathan, Percy Liang

* ACL 2020 

  Access Paper or Ask Questions

Understanding Self-Training for Gradual Domain Adaptation

Feb 26, 2020
Ananya Kumar, Tengyu Ma, Percy Liang


  Access Paper or Ask Questions

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy

Feb 25, 2020
Aditi Raghunathan, Sang Michael Xie, Fanny Yang, John Duchi, Percy Liang


  Access Paper or Ask Questions

Noise Induces Loss Discrepancy Across Groups for Linear Regression

Nov 22, 2019
Fereshte Khani, Percy Liang


  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


  Access Paper or Ask Questions

Learning Autocomplete Systems as a Communication Game

Nov 16, 2019
Mina Lee, Tatsunori B. Hashimoto, Percy Liang


  Access Paper or Ask Questions

Shaping Visual Representations with Language for Few-shot Classification

Nov 06, 2019
Jesse Mu, Percy Liang, Noah Goodman

* 9 pages inc. supplement; NeurIPS 2019 Workshop on Visually Grounded Interaction and Language (ViGIL) 

  Access Paper or Ask Questions

Verified Uncertainty Calibration

Sep 23, 2019
Ananya Kumar, Percy Liang, Tengyu Ma

* Accepted as a spotlight to NeurIPS 2019, original title was "Variance Reduced Uncertainty Calibration" 

  Access Paper or Ask Questions

Designing and Interpreting Probes with Control Tasks

Sep 08, 2019
John Hewitt, Percy Liang

* EMNLP 2019 

  Access Paper or Ask Questions

Distributionally Robust Language Modeling

Sep 04, 2019
Yonatan Oren, Shiori Sagawa, Tatsunori B. Hashimoto, Percy Liang

* Camera ready version for EMNLP 

  Access Paper or Ask Questions

Certified Robustness to Adversarial Word Substitutions

Sep 03, 2019
Robin Jia, Aditi Raghunathan, Kerem Göksel, Percy Liang

* EMNLP 2019 

  Access Paper or Ask Questions

A Tight Analysis of Greedy Yields Subexponential Time Approximation for Uniform Decision Tree

Jun 26, 2019
Ray Li, Percy Liang, Stephen Mussmann

* 40 pages, 5 figures 

  Access Paper or Ask Questions

Selection Via Proxy: Efficient Data Selection For Deep Learning

Jun 26, 2019
Cody Coleman, Christopher Yeh, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia


  Access Paper or Ask Questions

Adversarial Training Can Hurt Generalization

Jun 14, 2019
Aditi Raghunathan, Sang Michael Xie, Fanny Yang, John C. Duchi, Percy Liang


  Access Paper or Ask Questions

SPoC: Search-based Pseudocode to Code

Jun 12, 2019
Sumith Kulal, Panupong Pasupat, Kartik Chandra, Mina Lee, Oded Padon, Alex Aiken, Percy Liang

* Under submission to NeurIPS 2019 

  Access Paper or Ask Questions