Jacob Steinhardt

181 papers A* 59A 5B 1Journal 104Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Language Model Circuits Are Sparse in the Neuron Basis. CoRR Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt, Sarah Schwettmann
2026	J	`jnl`	Learning a Generative Meta-Model of LLM Activations. CoRR Grace Luo, Jiahai Feng, Trevor Darrell, Alec Radford, Jacob Steinhardt
2025	A*	`conf`	Adversaries Can Misuse Combinations of Safe Models. ICML Erik Jones, Anca D. Dragan, Jacob Steinhardt
2025	A*	`conf`	Eliciting Language Model Behaviors with Investigator Agents. ICML Xiang Lisa Li, Neil Chowdhury, Daniel D. Johnson, Tatsunori Hashimoto, Percy Liang, Sarah Schwettmann, Jacob Steinhardt
2025	J	`jnl`	Eliciting Language Model Behaviors with Investigator Agents. CoRR Xiang Lisa Li, Neil Chowdhury, Daniel D. Johnson, Tatsunori Hashimoto, Percy Liang, Sarah Schwettmann, Jacob Steinhardt
2025	J	`jnl`	Establishing Best Practices for Building Rigorous Agentic Benchmarks. CoRR Yuxuan Zhu, Tengjun Jin, Yada Pruksachatkun, Andy Zhang, Shu Liu, Sasha Cui, Sayash Kapoor, Shayne Longpre, Kevin Meng, Rebecca Weiss, Fazl Barez, Rahul Gupta, Jwala Dhamala, Jacob Merizian, Mario Giulianelli, Harry Coppock, Cozmin Ududec, Jasjeet S. Sekhon, Jacob Steinhardt, Antony Kellerman, Sarah Schwettmann, Matei Zaharia, Ion Stoica, Percy Liang, Daniel Kang
2025	A*	`conf`	Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts. ICML Jiahai Feng, Stuart Russell, Jacob Steinhardt
2025	A*	`conf`	Interpreting the Second-Order Effects of Neurons in CLIP. ICLR Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
2025	A*	`conf`	Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision. ICLR Yaowen Ye, Cassidy Laidlaw, Jacob Steinhardt
2025	J	`jnl`	Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision. CoRR Yaowen Ye, Cassidy Laidlaw, Jacob Steinhardt
2025	A*	`conf`	Language Models Learn to Mislead Humans via RLHF. ICLR Jiaxin Wen, Ruiqi Zhong, Akbir Khan, Ethan Perez, Jacob Steinhardt, Minlie Huang, Samuel R. Bowman, He He, Shi Feng
2025	A*	`conf`	Monitoring Latent World States in Language Models with Propositional Probes. ICLR Jiahai Feng, Stuart Russell, Jacob Steinhardt
2025	J	`jnl`	Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants. CoRR Vincent Huang, Dami Choi, Daniel D. Johnson, Sarah Schwettmann, Jacob Steinhardt
2025	J	`jnl`	Training Language Models to Explain Their Own Computations. CoRR Belinda Z. Li, Zifan Carl Guo, Vincent Huang, Jacob Steinhardt, Jacob Andreas
2025	A*	`conf`	Uncovering Gaps in How Humans and LLMs Interpret Subjective Language. ICLR Erik Jones, Arjun Patrawala, Jacob Steinhardt
2025	J	`jnl`	Uncovering Gaps in How Humans and LLMs Interpret Subjective Language. CoRR Erik Jones, Arjun Patrawala, Jacob Steinhardt
2025	J	`jnl`	Understanding In-context Learning of Addition via Activation Subspaces. CoRR Xinyan Hu, Kayo Yin, Michael I. Jordan, Jacob Steinhardt, Lijie Chen
2025	A*	`conf`	VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models. ICLR Lisa Dunlap, Krishna Mandal, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez
2025	A*	`conf`	What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning? ICML Katie Kang, Amrith Setlur, Dibya Ghosh, Jacob Steinhardt, Claire J. Tomlin, Sergey Levine, Aviral Kumar
2025	A*	`conf`	Which Attention Heads Matter for In-Context Learning? ICML Kayo Yin, Jacob Steinhardt
2025	J	`jnl`	Which Attention Heads Matter for In-Context Learning? CoRR Kayo Yin, Jacob Steinhardt
2024	J	`jnl`	Adversaries Can Misuse Combinations of Safe Models. CoRR Erik Jones, Anca D. Dragan, Jacob Steinhardt
2024	A*	`conf`	Approaching Human-Level Forecasting with Language Models. NeurIPS Danny Halawi, Fred Zhang, Chen Yueh-Han, Jacob Steinhardt
2024	J	`jnl`	Approaching Human-Level Forecasting with Language Models. CoRR Danny Halawi, Fred Zhang, Chen Yueh-Han, Jacob Steinhardt
2024	A*	`conf`	Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation. ICML Danny Halawi, Alexander Wei, Eric Wallace, Tony Tong Wang, Nika Haghtalab, Jacob Steinhardt
2024	J	`jnl`	Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation. CoRR Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, Jacob Steinhardt
2024	A*	`conf`	Describing Differences in Image Sets with Natural Language. CVPR Lisa Dunlap, Yuhui Zhang, Xiaohan Wang, Ruiqi Zhong, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez, Serena Yeung-Levy
2024	A*	`conf`	Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations. ICML Yanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao, He He, Jacob Steinhardt, Zhou Yu, Kathleen R. McKeown
2024	A*	`conf`	Explaining Datasets in Words: Statistical Models with Natural Language Parameters. NeurIPS Ruiqi Zhong, Heng Wang, Dan Klein, Jacob Steinhardt
2024	J	`jnl`	Explaining Datasets in Words: Statistical Models with Natural Language Parameters. CoRR Ruiqi Zhong, Heng Wang, Dan Klein, Jacob Steinhardt
2024	J	`jnl`	Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts. CoRR Jiahai Feng, Stuart Russell, Jacob Steinhardt
2024	A*	`conf`	Feedback Loops With Language Models Drive In-Context Reward Hacking. ICML Alexander Pan, Erik Jones, Meena Jagadeesan, Jacob Steinhardt
2024	J	`jnl`	Feedback Loops With Language Models Drive In-Context Reward Hacking. CoRR Alexander Pan, Erik Jones, Meena Jagadeesan, Jacob Steinhardt
2024	A*	`conf`	How do Language Models Bind Entities in Context? ICLR Jiahai Feng, Jacob Steinhardt
2024	A*	`conf`	Interpreting CLIP's Image Representation via Text-Based Decomposition. ICLR Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
2024	J	`jnl`	Interpreting the Second-Order Effects of Neurons in CLIP. CoRR Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
2024	J	`jnl`	Language Models Learn to Mislead Humans via RLHF. CoRR Jiaxin Wen, Ruiqi Zhong, Akbir Khan, Ethan Perez, Jacob Steinhardt, Minlie Huang, Samuel R. Bowman, He He, Shi Feng
2024	J	`jnl`	LatentQA: Teaching LLMs to Decode Activations Into Natural Language. CoRR Alexander Pan, Lijie Chen, Jacob Steinhardt
2024	J	`jnl`	Monitoring Latent World States in Language Models with Propositional Probes. CoRR Jiahai Feng, Stuart Russell, Jacob Steinhardt
2024	A*	`conf`	Overthinking the Truth: Understanding how Language Models Process False Demonstrations. ICLR Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt
2024	J	`jnl`	Safety vs. Performance: How Multi-Objective Learning Reduces Barriers to Market Entry. CoRR Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt
2024	J	`jnl`	VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models. CoRR Lisa Dunlap, Krishna Mandal, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez
2024	J	`jnl`	What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? CoRR Katie Kang, Amrith Setlur, Dibya Ghosh, Jacob Steinhardt, Claire J. Tomlin, Sergey Levine, Aviral Kumar
2023	A*	`conf`	Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations. ICML Yongyi Yang, Jacob Steinhardt, Wei Hu
2023	J	`jnl`	Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations. CoRR Yongyi Yang, Jacob Steinhardt, Wei Hu
2023	A*	`conf`	Automatically Auditing Large Language Models via Discrete Optimization. ICML Erik Jones, Anca D. Dragan, Aditi Raghunathan, Jacob Steinhardt
2023	J	`jnl`	Automatically Auditing Large Language Models via Discrete Optimization. CoRR Erik Jones, Anca D. Dragan, Aditi Raghunathan, Jacob Steinhardt
2023	J	`jnl`	Describing Differences in Image Sets with Natural Language. CoRR Lisa Dunlap, Yuhui Zhang, Xiaohan Wang, Ruiqi Zhong, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez, Serena Yeung-Levy
2023	A*	`conf`	Discovering Latent Knowledge in Language Models Without Supervision. ICLR Collin Burns, Haotian Ye, Dan Klein, Jacob Steinhardt
2023	J	`jnl`	Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations. CoRR Yanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao, He He, Jacob Steinhardt, Zhou Yu, Kathleen R. McKeown
2023	J	`jnl`	Eliciting Latent Predictions from Transformers with the Tuned Lens. CoRR Nora Belrose, Zach Furman, Logan Smith, Danny Halawi, Igor Ostrovsky, Lev McKinney, Stella Biderman, Jacob Steinhardt
2023	A*	`conf`	Goal Driven Discovery of Distributional Differences via Language Descriptions. NeurIPS Ruiqi Zhong, Peter Zhang, Steve Li, Jinwoo Ahn, Dan Klein, Jacob Steinhardt
2023	J	`jnl`	Goal Driven Discovery of Distributional Differences via Language Descriptions. CoRR Ruiqi Zhong, Peter Zhang, Steve Li, Jinwoo Ahn, Dan Klein, Jacob Steinhardt
2023	J	`jnl`	How do Language Models Bind Entities in Context? CoRR Jiahai Feng, Jacob Steinhardt
2023	A*	`conf`	Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition. NeurIPS Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt, Nika Haghtalab
2023	J	`jnl`	Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition. CoRR Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt, Nika Haghtalab
2023	J	`jnl`	Incentivizing High-Quality Content in Online Recommender Systems. CoRR Xinyan Hu, Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt
2023	A*	`conf`	Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small. ICLR Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, Jacob Steinhardt
2023	J	`jnl`	Interpreting CLIP's Image Representation via Text-Based Decomposition. CoRR Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
2023	A*	`conf`	Jailbroken: How Does LLM Safety Training Fail? NeurIPS Alexander Wei, Nika Haghtalab, Jacob Steinhardt
2023	J	`jnl`	Jailbroken: How Does LLM Safety Training Fail? CoRR Alexander Wei, Nika Haghtalab, Jacob Steinhardt
2023	J	`jnl`	Learning Equilibria in Matching Markets with Bandit Feedback. J. ACM Meena Jagadeesan, Alexander Wei, Yixin Wang, Michael I. Jordan, Jacob Steinhardt
2023	A*	`conf`	Mass-Producing Failures of Multimodal Systems with Language Models. NeurIPS Shengbang Tong, Erik Jones, Jacob Steinhardt
2023	J	`jnl`	Mass-Producing Failures of Multimodal Systems with Language Models. CoRR Shengbang Tong, Erik Jones, Jacob Steinhardt
2023	J	`jnl`	Overthinking the Truth: Understanding how Language Models Process False Demonstrations. CoRR Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt
2023	A*	`conf`	Progress measures for grokking via mechanistic interpretability. ICLR Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
2023	J	`jnl`	Progress measures for grokking via mechanistic interpretability. CoRR Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt
2023	A	`conf`	Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws. AISTATS Kush Bhatia, Wenshuo Guo, Jacob Steinhardt
2023	J	`jnl`	Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws. CoRR Kush Bhatia, Wenshuo Guo, Jacob Steinhardt
2023	A*	`conf`	Supply-Side Equilibria in Recommender Systems. NeurIPS Meena Jagadeesan, Nikhil Garg, Jacob Steinhardt
2022	—	`conf`	A3D: Studying Pretrained Representations with Programmable Datasets. CVPR Workshops Ye Wang, Norman Mu, Daniele Grandi, Nicolas Savva, Jacob Steinhardt
2022	J	`jnl`	Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior. CoRR Jean-Stanislas Denain, Jacob Steinhardt
2022	A*	`conf`	Capturing Failures of Large Language Models via Human Cognitive Biases. NeurIPS Erik Jones, Jacob Steinhardt
2022	J	`jnl`	Capturing Failures of Large Language Models via Human Cognitive Biases. CoRR Erik Jones, Jacob Steinhardt
2022	A*	`conf`	Describing Differences between Text Distributions with Natural Language. ICML Ruiqi Zhong, Charlie Snell, Dan Klein, Jacob Steinhardt
2022	J	`jnl`	Discovering Latent Knowledge in Language Models Without Supervision. CoRR Collin Burns, Haotian Ye, Dan Klein, Jacob Steinhardt
2022	A*	`conf`	Forecasting Future World Events With Neural Networks. NeurIPS Andy Zou, Tristan Xiao, Ryan Jia, Joe Kwon, Mantas Mazeika, Richard Li, Dawn Song, Jacob Steinhardt, Owain Evans, Dan Hendrycks
2022	J	`jnl`	Forecasting Future World Events with Neural Networks. CoRR Andy Zou, Tristan Xiao, Ryan Jia, Joe Kwon, Mantas Mazeika, Richard Li, Dawn Song, Jacob Steinhardt, Owain Evans, Dan Hendrycks
2022	A*	`conf`	How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios. NeurIPS Mantas Mazeika, Eric Tang, Andy Zou, Steven Basart, Jun Shern Chan, Dawn Song, David A. Forsyth, Jacob Steinhardt, Dan Hendrycks
2022	J	`jnl`	How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios. CoRR Mantas Mazeika, Eric Tang, Andy Zou, Steven Basart, Jun Shern Chan, Dawn Song, David A. Forsyth, Jacob Steinhardt, Dan Hendrycks
2022	J	`jnl`	Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small. CoRR Kevin Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, Jacob Steinhardt
2022	A*	`conf`	More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize. ICML Alexander Wei, Wei Hu, Jacob Steinhardt
2022	J	`jnl`	More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize. CoRR Alexander Wei, Wei Hu, Jacob Steinhardt
2022	A*	`conf`	PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures. CVPR Dan Hendrycks, Andy Zou, Mantas Mazeika, Leonard Tang, Bo Li, Dawn Song, Jacob Steinhardt
2022	A*	`conf`	Predicting Out-of-Distribution Error with the Projection Norm. ICML Yaodong Yu, Zitong Yang, Alexander Wei, Yi Ma, Jacob Steinhardt
2022	J	`jnl`	Predicting Out-of-Distribution Error with the Projection Norm. CoRR Yaodong Yu, Zitong Yang, Alexander Wei, Yi Ma, Jacob Steinhardt
2022	A*	`conf`	Scaling Out-of-Distribution Detection for Real-World Settings. ICML Dan Hendrycks, Steven Basart, Mantas Mazeika, Andy Zou, Joseph Kwon, Mohammadreza Mostajabi, Jacob Steinhardt, Dawn Song
2022	J	`jnl`	Stronger data poisoning attacks break data sanitization defenses. Mach. Learn. Pang Wei Koh, Jacob Steinhardt, Percy Liang
2022	J	`jnl`	Summarizing Differences between Text Distributions with Natural Language. CoRR Ruiqi Zhong, Charlie Snell, Dan Klein, Jacob Steinhardt
2022	J	`jnl`	Supply-Side Equilibria in Recommender Systems. CoRR Meena Jagadeesan, Nikhil Garg, Jacob Steinhardt
2022	A*	`conf`	The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models. ICLR Alexander Pan, Kush Bhatia, Jacob Steinhardt
2022	J	`jnl`	The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models. CoRR Alexander Pan, Kush Bhatia, Jacob Steinhardt
2021	A	`conf`	Agnostic Learning with Unknown Utilities. ITCS Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt
2021	J	`jnl`	Agnostic learning with unknown utilities. CoRR Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt
2021	A*	`conf`	Aligning AI With Shared Human Values. ICLR Dan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li, Dawn Song, Jacob Steinhardt
2021	J	`jnl`	Approximating How Single Head Attention Learns. CoRR Charlie Snell, Ruiqi Zhong, Dan Klein, Jacob Steinhardt
2021	—	`conf`	Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level. ACL/IJCNLP (Findings) Ruiqi Zhong, Dhruba Ghosh, Dan Klein, Jacob Steinhardt
2021	J	`jnl`	Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level. CoRR Ruiqi Zhong, Dhruba Ghosh, Dan Klein, Jacob Steinhardt
2021	A*	`conf`	Grounding Representation Similarity Through Statistical Testing. NeurIPS Frances Ding, Jean-Stanislas Denain, Jacob Steinhardt
2021	J	`jnl`	Grounding Representation Similarity with Statistical Testing. CoRR Frances Ding, Jean-Stanislas Denain, Jacob Steinhardt
2021	A*	`conf`	Learning Equilibria in Matching Markets from Bandit Feedback. NeurIPS Meena Jagadeesan, Alexander Wei, Yixin Wang, Michael I. Jordan, Jacob Steinhardt
2021	J	`jnl`	Learning Equilibria in Matching Markets from Bandit Feedback. CoRR Meena Jagadeesan, Alexander Wei, Yixin Wang, Michael I. Jordan, Jacob Steinhardt
2021	A*	`conf`	Limitations of Post-Hoc Feature Alignment for Robustness. CVPR Collin Burns, Jacob Steinhardt
2021	J	`jnl`	Limitations of Post-Hoc Feature Alignment for Robustness. CoRR Collin Burns, Jacob Steinhardt
2021	—	`conf`	Measuring Coding Challenge Competence With APPS. NeurIPS Datasets and Benchmarks Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob Steinhardt
2021	J	`jnl`	Measuring Coding Challenge Competence With APPS. CoRR Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob Steinhardt
2021	A*	`conf`	Measuring Massive Multitask Language Understanding. ICLR Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, Jacob Steinhardt
2021	—	`conf`	Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS Datasets and Benchmarks Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, Jacob Steinhardt
2021	J	`jnl`	Measuring Mathematical Problem Solving With the MATH Dataset. CoRR Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, Jacob Steinhardt
2021	A*	`conf`	Natural Adversarial Examples. CVPR Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, Dawn Song
2021	J	`jnl`	PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures. CoRR Dan Hendrycks, Andy Zou, Mantas Mazeika, Leonard Tang, Bo Li, Dawn Song, Jacob Steinhardt
2021	J	`jnl`	Technical perspective: Robust statistics tackle new problems. Commun. ACM Jacob Steinhardt
2021	J	`jnl`	The Effect of Model Size on Worst-Group Generalization. CoRR Alan Pham, Eunice Chan, Vikranth Srivatsa, Dhruba Ghosh, Yaoqing Yang, Yaodong Yu, Ruiqi Zhong, Joseph E. Gonzalez, Jacob Steinhardt
2021	A*	`conf`	The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization. ICCV Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer
2021	J	`jnl`	Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition. CoRR Yaodong Yu, Zitong Yang, Edgar Dobriban, Jacob Steinhardt, Yi Ma
2021	J	`jnl`	Unsolved Problems in ML Safety. CoRR Dan Hendrycks, Nicholas Carlini, John Schulman, Jacob Steinhardt
2021	—	`conf`	What Would Jiminy Cricket Do? Towards Agents That Behave Morally. NeurIPS Datasets and Benchmarks Dan Hendrycks, Mantas Mazeika, Andy Zou, Sahil Patel, Christine Zhu, Jesus Navarro, Dawn Song, Bo Li, Jacob Steinhardt
2021	J	`jnl`	What Would Jiminy Cricket Do? Towards Agents That Behave Morally. CoRR Dan Hendrycks, Mantas Mazeika, Andy Zou, Sahil Patel, Christine Zhu, Jesus Navarro, Dawn Song, Bo Li, Jacob Steinhardt
2020	J	`jnl`	Aligning AI With Shared Human Values. CoRR Dan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li, Dawn Song, Jacob Steinhardt
2020	A*	`conf`	Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming. NeurIPS Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, Aditi Raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian J. Goodfellow, Percy Liang, Pushmeet Kohli
2020	J	`jnl`	Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming. CoRR Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, Aditi Raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian J. Goodfellow, Percy Liang, Pushmeet Kohli
2020	A*	`conf`	Identifying Statistical Bias in Dataset Replication. ICML Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Madry
2020	J	`jnl`	Identifying Statistical Bias in Dataset Replication. CoRR Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Madry
2020	J	`jnl`	Measuring Massive Multitask Language Understanding. CoRR Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, Jacob Steinhardt
2020	A*	`conf`	Rethinking Bias-Variance Trade-off for Generalization of Neural Networks. ICML Zitong Yang, Yaodong Yu, Chong You, Jacob Steinhardt, Yi Ma
2020	J	`jnl`	Rethinking Bias-Variance Trade-off for Generalization of Neural Networks. CoRR Zitong Yang, Yaodong Yu, Chong You, Jacob Steinhardt, Yi Ma
2020	J	`jnl`	Robust estimation via generalized quasi-gradients. CoRR Banghua Zhu, Jiantao Jiao, Jacob Steinhardt
2020	J	`jnl`	The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization. CoRR Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer
2020	B	`conf`	When does the Tukey Median work? ISIT Banghua Zhu, Jiantao Jiao, Jacob Steinhardt
2020	J	`jnl`	When does the Tukey median work? CoRR Banghua Zhu, Jiantao Jiao, Jacob Steinhardt
2019	J	`jnl`	A Benchmark for Anomaly Segmentation. CoRR Dan Hendrycks, Steven Basart, Mantas Mazeika, Mohammadreza Mostajabi, Jacob Steinhardt, Dawn Song
2019	J	`jnl`	FrAngel: component-based synthesis with control structures. Proc. ACM Program. Lang. Kensen Shi, Jacob Steinhardt, Percy Liang
2019	J	`jnl`	Generalized Resilience and Robust Statistics. CoRR Banghua Zhu, Jiantao Jiao, Jacob Steinhardt
2019	J	`jnl`	Natural Adversarial Examples. CoRR Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, Dawn Song
2019	J	`jnl`	Research for practice: troubling trends in machine-learning scholarship. Commun. ACM Zachary C. Lipton, Jacob Steinhardt
2019	A*	`conf`	Sever: A Robust Meta-Algorithm for Stochastic Optimization. ICML Ilias Diakonikolas, Gautam Kamath, Daniel Kane, Jerry Li, Jacob Steinhardt, Alistair Stewart
2019	J	`jnl`	Testing Robustness Against Unforeseen Adversaries. CoRR Daniel Kang, Yi Sun, Dan Hendrycks, Tom Brown, Jacob Steinhardt
2019	J	`jnl`	Transfer of Adversarial Robustness Between Perturbation Types. CoRR Daniel Kang, Yi Sun, Tom Brown, Dan Hendrycks, Jacob Steinhardt
2019	J	`jnl`	Troubling Trends in Machine Learning Scholarship. ACM Queue Zachary C. Lipton, Jacob Steinhardt
2018	—	`conf`	Certified Defenses against Adversarial Examples. ICLR (Poster) Aditi Raghunathan, Jacob Steinhardt, Percy Liang
2018	J	`jnl`	Certified Defenses against Adversarial Examples. CoRR Aditi Raghunathan, Jacob Steinhardt, Percy Liang
2018	J	`jnl`	FrAngel: Component-Based Synthesis with Control Structures. CoRR Kensen Shi, Jacob Steinhardt, Percy Liang
2018	A	`conf`	Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers. ITCS Jacob Steinhardt, Moses Charikar, Gregory Valiant
2018	—	`—`	Robust learning: information theory and algorithms. Jacob Steinhardt
2018	A*	`conf`	Robust moment estimation and improved clustering via sum of squares. STOC Pravesh K. Kothari, Jacob Steinhardt, David Steurer
2018	A*	`conf`	Semidefinite relaxations for certifying robustness to adversarial examples. NeurIPS Aditi Raghunathan, Jacob Steinhardt, Percy Liang
2018	J	`jnl`	Semidefinite relaxations for certifying robustness to adversarial examples. CoRR Aditi Raghunathan, Jacob Steinhardt, Percy Liang
2018	J	`jnl`	Sever: A Robust Meta-Algorithm for Stochastic Optimization. CoRR Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Jacob Steinhardt, Alistair Stewart
2018	J	`jnl`	Stronger Data Poisoning Attacks Break Data Sanitization Defenses. CoRR Pang Wei Koh, Jacob Steinhardt, Percy Liang
2018	J	`jnl`	The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation. CoRR Miles Brundage, Shahar Avin, Jack Clark, Helen Toner, Peter Eckersley, Ben Garfinkel, Allan Dafoe, Paul Scharre, Thomas Zeitzoff, Bobby Filar, Hyrum S. Anderson, Heather Roff, Gregory C. Allen, Jacob Steinhardt, Carrick Flynn, Seán Ó hÉigeartaigh, Simon Beard, Haydn Belfield, Sebastian Farquhar, Clare Lyle, Rebecca Crootof, Owain Evans, Michael Page, Joanna Bryson, Roman Yampolskiy, Dario Amodei
2018	J	`jnl`	Troubling Trends in Machine Learning Scholarship. CoRR Zachary C. Lipton, Jacob Steinhardt
2017	J	`jnl`	Better Agnostic Clustering Via Relaxed Tensor Norms. CoRR Pravesh K. Kothari, Jacob Steinhardt
2017	—	`conf`	Certified Defenses for Data Poisoning Attacks. NIPS Jacob Steinhardt, Pang Wei Koh, Percy Liang
2017	J	`jnl`	Certified Defenses for Data Poisoning Attacks. CoRR Jacob Steinhardt, Pang Wei Koh, Percy Liang
2017	J	`jnl`	Does robustness imply tractability? A lower bound for planted clique in the semi-random model. CoRR Jacob Steinhardt
2017	J	`jnl`	Does robustness imply tractability? A lower bound for planted clique in the semi-random model. Electron. Colloquium Comput. Complex. Jacob Steinhardt
2017	A*	`conf`	Learning from untrusted data. STOC Moses Charikar, Jacob Steinhardt, Gregory Valiant
2017	J	`jnl`	Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers. CoRR Jacob Steinhardt, Moses Charikar, Gregory Valiant
2016	—	`conf`	Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction. NIPS Jacob Steinhardt, Gregory Valiant, Moses Charikar
2016	J	`jnl`	Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction. CoRR Jacob Steinhardt, Gregory Valiant, Moses Charikar
2016	J	`jnl`	Concrete Problems in AI Safety. CoRR Dario Amodei, Chris Olah, Jacob Steinhardt, Paul F. Christiano, John Schulman, Dan Mané
2016	J	`jnl`	Learning from Untrusted Data. CoRR Moses Charikar, Jacob Steinhardt, Gregory Valiant
2016	A*	`conf`	Memory, Communication, and Statistical Queries. COLT Jacob Steinhardt, Gregory Valiant, Stefan Wager
2016	—	`conf`	Unsupervised Risk Estimation Using Only Conditional Independence Structure. NIPS Jacob Steinhardt, Percy Liang
2016	J	`jnl`	Unsupervised Risk Estimation Using Only Conditional Independence Structure. CoRR Jacob Steinhardt, Percy Liang
2015	A*	`conf`	Learning Fast-Mixing Models for Structured Prediction. ICML Jacob Steinhardt, Percy Liang
2015	J	`jnl`	Learning Fast-Mixing Models for Structured Prediction. CoRR Jacob Steinhardt, Percy Liang
2015	A	`conf`	Learning Where to Sample in Structured Prediction. AISTATS Tianlin Shi, Jacob Steinhardt, Percy Liang
2015	—	`conf`	Learning with Relaxed Supervision. NIPS Jacob Steinhardt, Percy Liang
2015	J	`jnl`	Memory, Communication, and Statistical Queries. Electron. Colloquium Comput. Complex. Jacob Steinhardt, Gregory Valiant, Stefan Wager
2015	A*	`conf`	Minimax rates for memory-bounded sparse linear regression. COLT Jacob Steinhardt, John C. Duchi
2015	A*	`conf`	Reified Context Models. ICML Jacob Steinhardt, Percy Liang
2015	J	`jnl`	Reified Context Models. CoRR Jacob Steinhardt, Percy Liang
2014	A*	`conf`	Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm. ICML Jacob Steinhardt, Percy Liang
2014	A*	`conf`	Filtering with Abstract Particles. ICML Jacob Steinhardt, Percy Liang
2014	J	`jnl`	The Statistics of Streaming Sparse Regression. CoRR Jacob Steinhardt, Stefan Wager, Percy Liang
2012	J	`jnl`	Finite-time regional verification of stochastic non-linear systems. Int. J. Robotics Res. Jacob Steinhardt, Russ Tedrake
2012	A	`conf`	Flexible Martingale Priors for Deep Hierarchies. AISTATS Jacob Steinhardt, Zoubin Ghahramani
2011	—	`conf`	Finite-Time Regional Verification of Stochastic Nonlinear Systems. Robotics: Science and Systems Jacob Steinhardt, Russ Tedrake
2010	J	`jnl`	Permutations with Ascending and Descending Blocks. Electron. J. Comb. Jacob Steinhardt
2009	J	`jnl`	On Coloring the Odd-Distance Graph. Electron. J. Comb. Jacob Steinhardt