---
title: "Percy Liang — all works, page 2 — Elamur Research"
description: "All 356 works of Percy Liang in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/percy-liang/works/page/2/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/percy-liang/works/page/2/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Percy Liang](https://md.research.elamur.ai/free/en/authors/percy-liang/) / [all works](https://md.research.elamur.ai/free/en/authors/percy-liang/works/) / page 2

# Percy Liang — all works

356 works · page 2 of 4 · 101–200 · [← Percy Liang](https://md.research.elamur.ai/free/en/authors/percy-liang/)

[← prev](https://md.research.elamur.ai/free/en/authors/percy-liang/works/) [1](https://md.research.elamur.ai/free/en/authors/percy-liang/works/) **2** [3](https://md.research.elamur.ai/free/en/authors/percy-liang/works/page/3/) [4](https://md.research.elamur.ai/free/en/authors/percy-liang/works/page/4/) [next →](https://md.research.elamur.ai/free/en/authors/percy-liang/works/page/3/)

101. **[Certified Defenses for Data Poisoning Attacks ↗](https://arxiv.org/abs/1706.03691) arXiv (Cornell University) · no summary yet**Jacob Steinhardt, Pang Wei Koh, Percy Liang*2017 · 103 citations*
102. **[Linking People in Videos with “Their” Names Using Coreference Resolution ↗](https://doi.org/10.1007/978-3-319-10590-1_7) Lecture notes in computer science · no summary yet**Vignesh Ramanathan et al.*2014 · 103 citations*
103. **[Learning Programs: A Hierarchical Bayesian Approach ↗](https://openalex.org/W2131257014) no summary yet**Percy Liang, Michael I. Jordan, Dan Klein*2010 · 99 citations*
104. [**SPoC: Search-based Pseudocode to Code arXiv:1906.04908**Sumith Kulal, Panupong Pasupat, Kartik Chandra, et al.*2019 · 96 citations*](https://md.research.elamur.ai/free/en/papers/kulal-2019-spoc-search-based-pseudocode-code/)
105. **[Truncation Sampling as Language Model Desmoothing](https://md.research.elamur.ai/free/en/papers/hewitt-2022-truncation-sampling-as-language-model/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**John Hewitt, Christopher Manning, Percy Liang*2022 · 95 citations*
106. **[On the Accuracy of Influence Functions for Measuring Group Effects ↗](https://arxiv.org/abs/1905.13289) arXiv (Cornell University) · no summary yet**Pang Wei Koh et al.*2019 · 95 citations*
107. **[Imitation Learning of Agenda-based Semantic Parsers](https://md.research.elamur.ai/free/en/papers/berant-2015-imitation-learning-agenda-based-semantic/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Jonathan Berant, Percy Liang*2015 · 95 citations*
108. **[Calibrated Structured Prediction ↗](https://proceedings.neurips.cc/paper/2015) NeurIPS 2015 · no summary yet**Volodymyr Kuleshov, Percy Liang*2015 · 92 citations*
109. **[Unlabeled Data Improves Adversarial Robustness ↗](https://arxiv.org/abs/1905.13736) arXiv (Cornell University) · no summary yet**Yair Carmon et al.*2019 · 91 citations*
110. **[Language-Driven Representation Learning for Robotics ↗](https://doi.org/10.15607/rss.2023.xix.032) arXiv:2302.12766 · no summary yet**Siddharth Karamcheti et al.*2023 · 88 citations*
111. **[Naturalizing a Programming Language via Interactive Learning ↗](https://aclanthology.org/P17-1086/) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Sida I. Wang et al.*2017 · 87 citations*
112. **[MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records ↗](https://doi.org/10.1609/aaai.v38i20.30205) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Scott L. Fleming et al.*2024 · 82 citations*
113. [**BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text arXiv:2403.18421**Elliot Bolton, Abhinav Venigalla, Michihiro Yasunaga, et al.*2024 · 79 citations*](https://md.research.elamur.ai/free/en/papers/bolton-2024-biomedlm-2-7b-parameter-language/)
114. **[Picking on the Same Person: Does Algorithmic Monoculture Lead to Outcome Homogenization? ↗](https://doi.org/10.52202/068431-0265) neural information processing systems · no summary yet**Rishi Bommasani et al.*2022 · 78 citations*
115. **[A Probabilistic Approach to Diachronic Phonology ↗](https://aclanthology.org/D07-1093/) Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL) · no summary yet**Alexandre Bouchard et al.*2007 · 78 citations*
116. **[Holistic Evaluation of Text-to-Image Models ↗](https://doi.org/10.52202/075280-3067) neural information processing systems · no summary yet**Tony Lee et al.*2023 · 77 citations*
117. **[The Foundation Model Transparency Index ↗](https://arxiv.org/abs/2310.12941) arXiv:2310.12941 · no summary yet**Rishi Bommasani et al.*2023 · 76 citations*
118. **[Inferring Logical Forms From Denotations ↗](https://aclanthology.org/P16-1003/) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Panupong Pasupat, Percy Liang*2016 · 76 citations*
119. **[Environment-Driven Lexicon Induction for High-Level Instructions ↗](https://aclanthology.org/P15-1096/) Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yet**Dipendra Kumar Misra et al.*2015 · 76 citations*
120. [**Large Language Models as Analogical Reasoners arXiv:2310.01714**Michihiro Yasunaga, Xinyun Chen, Yujia Li, et al.*2023 · 74 citations*](https://md.research.elamur.ai/free/en/papers/yasunaga-2023-large-language-models-analogical-reasoners/)
121. **[Bringing Machine Learning and Compositional Semantics Together ↗](https://doi.org/10.1146/annurev-linguist-030514-125312) Annual Review of Linguistics 1:355–376 · no summary yet**Percy Liang, Christopher Potts*2015 · 73 citations*
122. **[Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training ↗](https://arxiv.org/abs/2305.14342) arXiv:2305.14342 · no summary yet**Hong Liu et al.*2023 · 70 citations*
123. **[Structure compilation ↗](https://doi.org/10.1145/1390156.1390231) International Conference on Machine Learning · no summary yet**Percy Liang, Hal Daumé, Dan Klein*2008 · 69 citations*
124. **[Surgical Fine-Tuning Improves Adaptation to Distribution Shifts ↗](https://arxiv.org/abs/2210.11466) arXiv (Cornell University) · no summary yet**Yoonho Lee et al.*2022 · 67 citations*
125. **[Macro Grammars and Holistic Triggering for Efficient Semantic Parsing](https://md.research.elamur.ai/free/en/papers/zhang-2017-macro-grammars-holistic-triggering-efficient/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Yuchen Zhang, Panupong Pasupat, Percy Liang*2017 · 67 citations*
126. **[Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making ↗](https://doi.org/10.52202/079017-3188) neural information processing systems · no summary yet**Feifei Li et al.*2024 · 66 citations*
127. **[RNNs can generate bounded hierarchical languages with optimal memory](https://md.research.elamur.ai/free/en/papers/hewitt-2020-rnns-can-generate-bounded-hierarchical/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**John Hewitt, Michael Hahn, Surya Ganguli, et al.*2020 · 65 citations*
128. **[LM-Critic: Language Models for Unsupervised Grammatical Error Correction ↗](https://aclanthology.org/2021.emnlp-main.611/) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · no summary yet**Michihiro Yasunaga, Jure Leskovec, Percy Liang*2021 · 63 citations*
129. **[Conditional probing: measuring usable information beyond a baseline ↗](https://aclanthology.org/2021.emnlp-main.122/) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · no summary yet**John Hewitt et al.*2021 · 62 citations*
130. **[Break-It-Fix-It: Unsupervised Learning for Program Repair ↗](https://arxiv.org/abs/2106.06600) arXiv:2106.06600 · no summary yet**Michihiro Yasunaga, Percy Liang*2021 · 62 citations*
131. **[No, to the Right ↗](https://doi.org/10.1145/3568162.3578623) ACM/IEEE International Conference on Human-Robot Interaction (HRI) · no summary yet**Yuchen Cui et al.*2023 · 61 citations*
132. **[Decentralized Training of Foundation Models in Heterogeneous Environments ↗](https://arxiv.org/abs/2206.01288) arXiv:2206.01288 · no summary yet**Binhang Yuan et al.*2022 · 59 citations*
133. **[Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization ↗](https://arxiv.org/abs/2107.04649) arXiv (Cornell University) · no summary yet**John J. Miller et al.*2021 · 59 citations*
134. **[Video Event Understanding Using Natural Language Descriptions ↗](https://doi.org/10.1109/iccv.2013.117) IEEE International Conference on Computer Vision (ICCV) · no summary yet**Vignesh Ramanathan, Percy Liang, Li Fei-Fei*2013 · 59 citations*
135. **[Understanding and Mitigating the Tradeoff Between Robustness and Accuracy ↗](https://arxiv.org/abs/2002.10716) arXiv (Cornell University) · no summary yet**Aditi Raghunathan et al.*2020 · 58 citations*
136. **[Spectral Experts for Estimating Mixtures of Linear Regressions ↗](https://arxiv.org/abs/1306.3729) arXiv (Cornell University) · no summary yet**Arun Tejasvi Chaganty, Percy Liang*2013 · 58 citations*
137. **[A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics ↗](https://arxiv.org/abs/1702.05575) arXiv (Cornell University) · no summary yet**Yuchen Zhang, Percy Liang, Moses Charikar*2017 · 57 citations*
138. **[Foundation Model Transparency Reports ↗](https://doi.org/10.1609/aies.v7i1.31628) Proceedings of the AAAI/ACM Conference on AI Ethics and Society · no summary yet**Rishi Bommasani et al.*2024 · 53 citations*
139. **[Zero-shot Entity Extraction from Web Pages ↗](https://aclanthology.org/P14-1037/) Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Panupong Pasupat, Percy Liang*2014 · 53 citations*
140. **[ExpBERT: Representation Engineering with Natural Language Explanations ↗](https://aclanthology.org/2020.acl-main.190/) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yet**Shikhar Murty, Pang Wei Koh, Percy Liang*2020 · 52 citations*
141. **[Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models ↗](https://arxiv.org/abs/2402.07865) arXiv (Cornell University) · no summary yet**Siddharth Karamcheti et al.*2024 · 51 citations*
142. **[The price of debiasing automatic metrics in natural language evaluation ↗](https://arxiv.org/abs/1807.02202) arXiv (Cornell University) · no summary yet**Arun Tejasvi Chaganty, Stephen Mussmann, Percy Liang*2018 · 51 citations*
143. **[Agreement-Based Learning ↗](https://openalex.org/W2163403121) no summary yet**Percy Liang, Dan Klein, Michael I. Jordan*2007 · 51 citations*
144. **[Learning nongenerative grammatical models for document analysis ↗](https://doi.org/10.1109/iccv.2005.140) no summary yet**Michael Shilman, Percy Liang, Paul A. Viola*2005 · 50 citations*
145. **[Mapping natural language commands to web elements ↗](https://aclanthology.org/D18-1540/) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yet**Panupong Pasupat et al.*2018 · 49 citations*
146. **[Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm ↗](https://openalex.org/W95741308) no summary yet**Jacob Steinhardt, Percy Liang*2014 · 48 citations*
147. **[The EOS Decision and Length Extrapolation ↗](https://aclanthology.org/2020.blackboxnlp-1.26/) Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · no summary yet**Benjamin Newman et al.*2020 · 47 citations*
148. **[Robustness to Spurious Correlations via Human Annotations ↗](https://arxiv.org/abs/2007.06661) arXiv (Cornell University) · no summary yet**Megha Srivastava, Tatsunori Hashimoto, Percy Liang*2020 · 47 citations*
149. **[Type-Based MCMC ↗](https://aclanthology.org/N10-1082/) Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics · no summary yet**Percy Liang, Michael I. Jordan, Dan Klein*2010 · 47 citations*
150. **[Tensor Factorization via Matrix Factorization ↗](https://arxiv.org/abs/1501.07320) arXiv (Cornell University) · no summary yet**Volodymyr Kuleshov, Arun Tejasvi Chaganty, Percy Liang*2015 · 45 citations*
151. **[Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately ↗](https://doi.org/10.1145/3442188.3445883) ACM Conference on Fairness, Accountability, and Transparency (FAccT) · no summary yet**Fereshte Khani, Percy Liang*2021 · 44 citations*
152. **[Shaping Visual Representations with Language for Few-Shot Classification ↗](https://aclanthology.org/2020.acl-main.436/) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yet**Jesse Mu, Percy Liang, Noah Goodman*2020 · 44 citations*
153. **[FrAngel: component-based synthesis with control structures ↗](https://doi.org/10.1145/3290386) Proceedings of the ACM on Programming Languages · no summary yet**Kensen Shi, Jacob Steinhardt, Percy Liang*2019 · 44 citations*
154. **[Learning minimal abstractions ↗](https://doi.org/10.1145/1926385.1926391) ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL) · no summary yet**Percy Liang, Omer Tripp, Mayur Naik*2011 · 44 citations*
155. **[Developing Bug-Free Machine Learning Systems With Formal Mathematics ↗](https://arxiv.org/abs/1706.08605) arXiv:1706.08605 · no summary yet**Daniel Selsam, Percy Liang, David L. Dill*2017 · 42 citations*
156. **[Scaling abstraction refinement via pruning ↗](https://doi.org/10.1145/1993498.1993567) Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation · no summary yet**Percy Liang, Mayur Naik*2011 · 40 citations*
157. **[Understanding Self-Training for Gradual Domain Adaptation ↗](https://arxiv.org/abs/2002.11361) arXiv (Cornell University) · no summary yet**Ananya Kumar, Tengyu Ma, Percy Liang*2020 · 39 citations*
158. **[Identifiability and Unmixing of Latent Parse Trees ↗](https://arxiv.org/abs/1206.3137) arXiv (Cornell University) · no summary yet**Daniel Hsu, Sham M. Kakade, Percy Liang*2012 · 38 citations*
159. **[Feature Noising for Log-Linear Structured Prediction ↗](https://aclanthology.org/D13-1117/) Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · no summary yet**Sida Wang et al.*2013 · 37 citations*
160. **[Analyzing the Errors of Unsupervised Learning ↗](https://aclanthology.org/P08-1100/) Proceedings of ACL-08: HLT · no summary yet**Percy Liang, Dan Klein*2008 · 37 citations*
161. **[Structure Compilation: Trading Structure for Features ↗](https://openalex.org/W7097794200) no summary yet**Percy Liang, Hal Daumé Iii, Dan Klein*2008 · 37 citations*
162. **[Considerations for governing open foundation models ↗](https://doi.org/10.1126/science.adp1848) Science · no summary yet**Rishi Bommasani et al.*2024 · 36 citations*
163. **[VHELM: A Holistic Evaluation of Vision Language Models ↗](https://doi.org/10.52202/079017-4464) neural information processing systems · no summary yet**Tong Lee et al.*2024 · 34 citations*
164. **[Learning Adaptive Language Interfaces through Decomposition ↗](https://aclanthology.org/2020.intexsempar-1.4/) Proceedings of the First Workshop on Interactive and Executable Semantic Parsing · no summary yet**Siddharth Karamcheti, Dorsa Sadigh, Percy Liang*2020 · 34 citations*
165. **[Can Small and Synthetic Benchmarks Drive Modeling Innovation? A Retrospective Study of Question Answering Modeling Approaches. ↗](https://arxiv.org/abs/2102.01065) arXiv (Cornell University) · no summary yet**Nelson F. Liu et al.*2021 · 33 citations*
166. **[Convexified Convolutional Neural Networks ↗](https://arxiv.org/abs/1609.01000) arXiv (Cornell University) · no summary yet**Yuchen Zhang, Percy Liang, Martin J. Wainwright*2016 · 33 citations*
167. **[Codified audio language modeling learns useful representations for music information retrieval ↗](https://arxiv.org/abs/2107.05677) arXiv (Cornell University) · no summary yet**Rodrigo Castellon, Chris Donahue, Percy Liang*2021 · 31 citations*
168. **[Planning, Inference and Pragmatics in Sequential Language Games](https://md.research.elamur.ai/free/en/papers/khani-2018-planning-inference-pragmatics-sequential-language/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Fereshte Khani, Noah D. Goodman, Percy Liang*2018 · 31 citations*
169. **[On the Societal Impact of Open Foundation Models ↗](https://arxiv.org/abs/2403.07918) arXiv (Cornell University) · no summary yet**Sayash Kapoor et al.*2024 · 30 citations*
170. **[BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments ↗](https://arxiv.org/abs/2405.17631) arXiv:2405.17631 · no summary yet**Yusuf Roohani et al.*2024 · 29 citations*
171. **[Prediction with a short memory ↗](https://doi.org/10.1145/3188745.3188954) ACM SIGACT Symposium on Theory of Computing (STOC) · no summary yet**Vatsal Sharan et al.*2016 · 29 citations*
172. **[On the Learnability of Watermarks for Language Models ↗](https://arxiv.org/abs/2312.04469) arXiv (Cornell University) · no summary yet**Chenchen Gu et al.*2023 · 28 citations*
173. **[Backpack Language Models ↗](https://aclanthology.org/2023.acl-long.506/) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**John Hewitt et al.*2023 · 27 citations*
174. **[Benchmarking and Improving Generator-Validator Consistency of Language Models ↗](https://arxiv.org/abs/2310.01846) arXiv (Cornell University) · no summary yet**Xiang Lisa Li et al.*2023 · 27 citations*
175. **[Importance sampling for unbiased on-demand evaluation of knowledge base population ↗](https://aclanthology.org/D17-1109/) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · no summary yet**Arun Chaganty et al.*2017 · 27 citations*
176. **[Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts ↗](https://aclanthology.org/D18-1008/) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yet**Matthew Lamm et al.*2018 · 26 citations*
177. **[Advancing science- and evidence-based AI policy ↗](https://doi.org/10.1126/science.adu8449) Science · no summary yet**Rishi Bommasani et al.*2025 · 25 citations*
178. **[Estimating Latent-Variable Graphical Models using Moments and Likelihoods ↗](https://openalex.org/W43873609) no summary yet**Arun Tejasvi Chaganty, Percy Liang*2014 · 25 citations*
179. **[A dynamic evaluation of the precision of static heap abstractions ↗](https://doi.org/10.1145/1869459.1869494) ACM International Conference on Object Oriented Programming Systems Languages and Applications (OOPSLA) · no summary yet**Percy Liang et al.*2010 · 25 citations*
180. **[Probabilistic grammars and hierarchical Dirichlet processes ↗](https://doi.org/10.1093/oxfordhb/9780198703174.013.27) Oxford University Press eBooks · no summary yet**Percy Liang, Michael I. Jordan, Dan Klein*24 citations*
181. **[AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies ↗](https://doi.org/10.70777/si.v1i1.10863) SuperIntelligence - Robotics - Safety & Alignment · no summary yet**Yi Zeng et al.*2024 · 23 citations*
182. **[Ecosystem Graphs: The Social Footprint of Foundation Models ↗](https://doi.org/10.21203/rs.3.rs-2961271/v1) Research Square · no summary yet**Rishi Bommasani et al.*2023 · 23 citations*
183. **[Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation ↗](https://arxiv.org/abs/2311.08877) arXiv (Cornell University) · no summary yet**Vaishnavi Shrivastava, Percy Liang, Ananya Kumar*2023 · 23 citations*
184. **[Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation ↗](https://arxiv.org/abs/2204.00570) arXiv (Cornell University) · no summary yet**Kendrick Shen et al.*2022 · 23 citations*
185. **[Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality ↗](https://aclanthology.org/2021.naacl-main.345/) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Mina Lee et al.*2021 · 23 citations*
186. **[AutoBencher: Towards Declarative Benchmark Construction ↗](https://arxiv.org/abs/2407.08351) arXiv (Cornell University) · no summary yet**Xiang Lisa Li et al.*2024 · 22 citations*
187. **[A Safe Harbor for AI Evaluation and Red Teaming ↗](https://arxiv.org/abs/2403.04893) arXiv (Cornell University) · no summary yet**Shayne Longpre et al.*2024 · 22 citations*
188. **[Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models ↗](https://arxiv.org/abs/2408.08926) arXiv (Cornell University) · no summary yet**Andy K. Zhang et al.*2024 · 22 citations*
189. **[Insights into Pre-Training Via Simpler Synthetic Tasks ↗](https://doi.org/10.52202/068431-1588) neural information processing systems · no summary yet**Yuhuai Wu, Felix Li, Percy Liang*2022 · 22 citations*
190. **[PRODIGY: Enabling In-context Learning Over Graphs ↗](https://doi.org/10.52202/075280-0718) neural information processing systems · no summary yet**Qian Huang et al.*2023 · 21 citations*
191. **[Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming ↗](https://arxiv.org/abs/2010.11645) arXiv:2010.11645 · no summary yet**Sumanth Dathathri et al.*2020 · 21 citations*
192. **[On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks ↗](https://aclanthology.org/2020.findings-emnlp.305/) Findings of the Association for Computational Linguistics: EMNLP 2020 · no summary yet**Stephen Mussmann, Robin Jia, Percy Liang*2020 · 21 citations*
193. **[Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings ↗](https://aclanthology.org/P16-1090/) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Fereshte Khani, Martin Rinard, Percy Liang*2016 · 20 citations*
194. **[Unsupervised Risk Estimation Using Only Conditional Independence Structure ↗](https://arxiv.org/abs/1606.05313) arXiv (Cornell University) · no summary yet**Jacob Steinhardt, Percy Liang*2016 · 20 citations*
195. **[Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning ↗](https://arxiv.org/abs/2601.16163) arXiv (Cornell University) · no summary yet**Moo Jin Kim et al.*2026 · 19 citations*
196. **[Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective ↗](https://arxiv.org/abs/2410.05192) arXiv (Cornell University) · no summary yet**Kaiyue Wen et al.*2024 · 18 citations*
197. **[Extending the WILDS Benchmark for Unsupervised Adaptation ↗](https://arxiv.org/abs/2112.05090) arXiv (Cornell University) · no summary yet**Shiori Sagawa et al.*2021 · 18 citations*
198. **[In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness ↗](https://arxiv.org/abs/2012.04550) arXiv (Cornell University) · no summary yet**Sang Michael Xie et al.*2020 · 18 citations*
199. **[Altitude Training: Strong Bounds for Single-Layer Dropout ↗](https://arxiv.org/abs/1407.3289) arXiv (Cornell University) · no summary yet**Stefan Wager et al.*2014 · 18 citations*
200. **[Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research ↗](https://doi.org/10.52202/085713-2990) neural information processing systems · no summary yet**A. Feder Cooper et al.*2025 · 17 citations*

[← prev](https://md.research.elamur.ai/free/en/authors/percy-liang/works/) [1](https://md.research.elamur.ai/free/en/authors/percy-liang/works/) **2** [3](https://md.research.elamur.ai/free/en/authors/percy-liang/works/page/3/) [4](https://md.research.elamur.ai/free/en/authors/percy-liang/works/page/4/) [next →](https://md.research.elamur.ai/free/en/authors/percy-liang/works/page/3/)