Google Scholar; Twitter; GitHub; My research is driven by a fundamental passion for building reliable artificial intelligence (AI) technologies for medical decision making. Bio: Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. Twitter Facebook LinkedIn … ∙ 2 https://hai.stanford.edu/events/hai-weekly-seminar-percy-liang 11/22/2019 ∙ by Fereshte Khani, et al. Percy Liang (Stanford+CodaLab) Victoria Stodden (UIUC) Joaquin Vanschoren (TU/e+OpenML). Gates 250 / pliang@cs.stanford.edu [Publications] Research. Advisor: Percy Liang. ∙ Alpha Go reportedly used this algorithm with a … ∙ When Percy Liang isn't creating algorithms, he's creating musical rhythms. Don't have an account? ∙ Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang. share, We present a simple approach for text infilling, the task of predicting Stanford University, Assistant Professor at Stanford University, Fine-tuning is the de facto way to leverage large pretrained language mo... ∙ 106, Unsupervised deep clustering and reinforcement learning can accurately Percy Liang, Assistant Professor of Computer Science at Stanford University, explains that humans rely on some degree of predictability in their day-to-day interactions — both with other humans and automated systems (including, but not limited to, their cars). ∙ When Percy Liang isn't creating algorithms, he's creating musical rhythms. See more details here. share, Existing studies on question answering on knowledge bases (KBQA) mainly 11/13/2018 ∙ by Kensen Shi, et al. share, We consider the task of mapping pseudocode to long programs that are Jitendra Malik 98 publications . 0 Liang Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang. from MIT, 2004; Ph.D. from UC Berkeley, 2011). In Proceedings of the … Singapore - Transferable Semi-supervised 3D Object Detection from RGB-D Data ∙ ∙ Percy Liang | Vancouver, Canada Area | Project Manager at Government of Canada | 8 connections | See Percy's complete profile on Linkedin and connect 01/25/2019 ∙ by Hatef Monajemi, et al. ∙ share, Adversarial perturbations dramatically decrease the accuracy of 05/11/2020 ∙ by Chris Donahue, et al. The best way to contact me is email: sidawxyz [at] gmail.com. Show more Show less. from MIT, 2004; Ph.D. from UC Berkeley, 2011). from MIT, 2004; Ph.D. from UC Berkeley, 2011). share, Uncertainty sampling, a popular active learning algorithm, is used to re... hypot... Distributionally robust neural networks for group shifts: On the … share, Despite their impressive performance on diverse tasks, neural networks f... ∙ 0 Feature Noise Induces Loss Discrepancy Across Groups, Fereshte Khani, share, We describe an approach to task-oriented dialogue in which dialogue stat... share, Despite excellent performance on many tasks, NLP systems are easily fool... Led section for … from MIT, 2004; Ph.D. from UC Berkeley, 2011). 6 share, Are you a researcher?Expose your workto one of the largestA.I. ∙ 06/29/2020 ∙ by Sang Michael Xie, et al. Bryan Anenberg’s personal website. ∙ share, We study textual autocomplete—the task of predicting a full sentence fro... STAT 205 Probability Theory Fall 2006 Topic: Inversion formula Lecturer: Jim Pitman, Scribe: Bo Li, Ankit Jain, Percy Liang, Editor: ∙ I am a computer vision engineer at Anduril Industries, where I work on defense technologies.I received a Master’s in Computer Science from Stanford in 2017, where I studied computer vision, machine learning, deep learning, and natural language processing. 04/04/2019 ∙ by Tatsunori B. Hashimoto, et al. Bryan Anenberg’s personal website. ∙ Out-of-Distribution Robustness, Removing Spurious Features can Hurt Accuracy and Affect Groups 12 share, In component-based program synthesis, the synthesizer generates a progra... 0 121, Computational principles of intelligence: learning and reasoning with 05/04/2020 ∙ by Erik Jones, et al. 14 3 Parseval’s Identity Lemma 1 (Parseval’s identity) ϕ X (y) G (dy) = ϕ Y (x) F (dx). ∙ ∙ 42 09/04/2019 ∙ by Yonatan Oren, et al. Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. ∙ 23 Jaebum has 4 jobs listed on their profile. The model gave an F1 score of 93.011. 12/04/2018 ∙ by Tatsunori B. Hashimoto, et al. share, Selective classification, in which models are allowed to abstain on unce... Percy Liang 99 publications . ∙ 0 09/24/2020 ∙ by Jacob Andreas, et al. Papers (by Topic) / Teaching & Service About. Percy Shuo Liang EECS Department University of California, Berkeley Technical Report No. Fei has 6 jobs listed on their profile. 01/01/2021 ∙ by Xiang Lisa Li, et al. Bio: Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers easier to communicate with through natural language. ∙ 0 Visualizza il profilo di Margherita Campart su LinkedIn, la più grande comunità professionale al mondo. share, Suppose we want to specify the inductive bias that married couples typic... ∙ Guarda il profilo completo su LinkedIn e scopri i collegamenti di Margherita e le offerte di lavoro presso aziende simili. 14 Monte Carlo Tree search is a fancy name for one Artificial Intelligence algorithm used specially in games. See the complete profile on LinkedIn and discover Geok Lan’s connections and jobs at similar companies. Pairwise Tasks, Task-Oriented Dialogue as Dataflow Synthesis, Explore then Execute: Adapting without Rewards via Factorized 07/12/2020 ∙ by Evan Zheran Liu, et al. 118, When Machine Learning Meets Quantum Computers: A Case Study, 12/18/2020 ∙ by Weiwen Jiang ∙ communities in the world, Get the week's mostpopular data scienceresearch in your inbox -every Saturday, Explainability in Graph Neural Networks: A Taxonomic Survey, 12/31/2020 ∙ by Hao Yuan ∙ 11/02/2018 ∙ by Aditi Raghunathan, et al. His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers easier to communicate with through natural language. 0 I am a PhD student at Stanford University advised by share, The reliability of machine learning systems critically assumes that the in … I'm a first-year Ph.D. student in the Department of Computer Science at Stanford University, affiliated with the Stanford NLP group and the Stanford AI Laboratory. I am an assistant professor of computer science and statistics at Stanford. ... share, We seek to efficiently learn by leveraging shared structure between diff... ∙ f... 05/31/2019 ∙ by Yair Carmon, et al. Percy Liang Michael Jordan Statistical and computational concerns have motivated parameter estimators based on various forms of likelihood, e.g., joint, condi- tional, and pseudolikelihood. ∙ View inversion.pdf from STAT 205 at San Diego State University. share, We demonstrate, theoretically and empirically, that adversarial robustne... ∙ 0 ∙ 05/05/2020 ∙ by Shikhar Murty, et al. Percy Liang, a Stanford CS professor and NLP expert, breaks down the various approaches to NLP / NLU into four distinct categories: 1) Distributional 2) Frame-based 3) Model-theoretical 4) Interactive learning. Sida I. Wang, Samuel Ginn, Percy Liang, Christopher D Manning. ... s... ∙ ope... 05/20/2020 ∙ by Michihiro Yasunaga, et al. ∙ Discretization, Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on ∙ Percy Liang Associate Professor of Computer Science, Stanford University Verified email at cs.stanford.edu. 10/22/2020 ∙ by Sumanth Dathathri, et al. share, Though machine learning algorithms excel at minimizing the average loss ... 0 Kelvin Guu 11 publications . 0 wondered if it is possible to develop fair systems even when we don’t have demographic information. Alpha Go reportedly used this algorithm with a … share, The presence of spurious features interferes with the goal of obtaining 10/15/2020 ∙ by John Hewitt, et al. ∙ Disproportionately, Beyond I.I.D. ∙ share, Recurrent neural networks empirically generate natural language with hig... ∙ The problem is that small groups have a low representation in minimizing the average training loss. 93, Learning emergent PDEs in a learned emergent space, 12/23/2020 ∙ by Felix P. Kemeth ∙ You can change your ad preferences anytime. Meta-Reinforcement Learning, Robustness to Spurious Correlations via Human Annotations, Learning Abstract Models for Strategic Exploration and Fast Reward share, We study why overparameterization – increasing model size well beyond th... Margherita ha indicato 6 esperienze lavorative sul suo profilo. communities, Join one of the world's largest A.I. ∙ neural networks, 12/17/2020 ∙ by Abel Torres Montoya ∙ 07/09/2020 ∙ by Pang Wei Koh, et al. Christian Henriot and Wen-hsin Yeh 2. share, Machine learning models trained on data from the outside world can be ∙ Percy Liang View As in [8, 24, 32], we model the aforementioned relation using a transition probability, which is the distribution of the observable variable conditioned on the label and instance. share, Modern data science research can involve massive computational ∙ Association for Computational Linguistics (ACL), 2017. fun... ∙ ∙ share, Overparameterized neural networks can be highly accurate on average on a... memory-efficient semidefinite programming, RNNs can generate bounded hierarchical languages with optimal memory, The EOS Decision and Length Extrapolation, Learning Adaptive Language Interfaces through Decomposition, On the Importance of Adaptive Data Collection for Extremely Imbalanced 08/06/2020 ∙ by Evan Zheran Liu, et al. from MIT, 2004; Ph.D. from UC Berkeley, 2011). The dataset was presented by researchers: Pranav Rajpurkar and Jian Zhang and Konstantin Lopyrev and Percy Liang from Stanford University. 09/23/2019 ∙ by Ananya Kumar, et al. 0 12 © Stanford University, Stanford, California 94305. View Harriet King’s professional profile on LinkedIn. STAT 205 Probability Theory Fall 2006 Topic: Parseval’s identity Lecturer: Jim Pitman, Scribe: Ankit Jain, Percy Liang, Editor: Ying Xu 1 Prerequisites Integral 2 Summary This identity will be used to derive the inversion formula of characteristic fuction. 12/07/2020 ∙ by Fereshte Khani, et al. ∙ The current state of the art framework on the SQuAD dataset is SA-Net on Albert. I am an assistant professor of computer science and statistics at Stanford. ∙ 0 ∙ Question Answering is a technique inside the fields of natural language processing, which is concerned about building frameworks that consequently answer addresses presented by people in natural language processing.The capacity to peruse the content and afterward answer inquiries concerning it, is a difficult undertaking for machines, requiring information about the world. Percy Liang, a Stanford CS professor and NLP expert, breaks down the various approaches to NLP / NLU into four distinct categories: 1) Distributional 2) Frame-based 3) Model-theoretical 4) Interactive learning. ∙ Bio. Papers (by Topic) / Teaching & Service About. I am currently on the academic job market (2020-2021) pranavsr@cs.stanford.edu. His awards include the Presidential Early Career Award for Scientists and Engineers (2019), IJCAI Computers and Thought Award (2016), an NSF CAREER Award (2016), a Sloan Research Fellowship (2015), and a Microsoft Research Faculty Fellowship (2014). 0 06/14/2019 ∙ by Aditi Raghunathan, et al. 09/08/2019 ∙ by John Hewitt, et al. Awni Hannun Facebook AI Research Verified email at fb.com. 05/30/2019 ∙ by Pang Wei Koh, et al. 0 0 View Liang Hui Tan’s profile on LinkedIn, the world's largest professional community. LinkedIn is the world’s largest business network, helping professionals like Harriet King discover inside connections to recommended job candidates, industry experts, and business partners. share, How can we measure whether a natural language generation system produces... 12/08/2020 ∙ by Sang Michael Xie, et al. share, Probes, supervised models trained to predict properties (like ... in … 0 ∙ 2013. The dataset was presented by researchers: Pranav Rajpurkar and Jian Zhang and Konstantin Lopyrev and Percy Liang from Stanford University. state-of... share, Influence functions estimate the effect of removing particular training 12/14/2020 ∙ by Pang Wei Koh, et al. 6 92, Meta Learning Backpropagation And Improving It, 12/29/2020 ∙ by Louis Kirsch ∙ 0 ∙ experimen... Zero-One Loss, A Retrieve-and-Edit Framework for Predicting Structured Outputs, FrAngel: Component-Based Synthesis with Control Structures, Semidefinite relaxations for certifying robustness to adversarial share, Many pairwise classification tasks, such as paraphrase detection and 0 Percy Liang 102 publications . communities claim Claim with Google Claim with Twitter Claim with GitHub Claim with LinkedIn There are 4 professionals named "Percy Liang", who use LinkedIn to exchange information, ideas, and opportunities. ... share, Many applications of machine learning in science and medicine, including... : Three Levels of Generalization for Question Answering on 最先端NLP勉強会 “Learning Language Games through Interaction” Sida I. Wang, Percy Liang, Christopher D. Manning ∙ ∙ If you are a student at NYU, please drop me an email. Rishi Bommasani. Advisor: Percy Liang. 227, 12/20/2020 ∙ by Johannes Czech ∙ Monte Carlo Tree search is a fancy name for one Artificial Intelligence algorithm used specially in games. https://hai.stanford.edu/events/hai-weekly-seminar-percy-liang Ph.D. Committee: Percy Liang, Wing Hung Wong, Chris Manning, and Lester Mackey. 91, Claim your profile and join one of the world's largest A.I. ∙ 8 04/15/2019 ∙ by He He, et al. share, Our goal is to create an interactive natural language interface that I am currently on the academic job market (2020-2021) pranavsr@cs.stanford.edu. Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. examples, Stronger Data Poisoning Attacks Break Data Sanitization Defenses. ∙ ∙ Your source for engineering research and ideas. parts-of-s... Importance of Regularization for Worst-Case Generalization, Learning Autocomplete Systems as a Communication Game, Shaping Visual Representations with Language for Few-shot Classification, Designing and Interpreting Probes with Control Tasks, Distributionally Robust Language Modeling, Certified Robustness to Adversarial Word Substitutions, A Tight Analysis of Greedy Yields Subexponential Time Approximation for 10/27/2020 ∙ by Erik Jones, et al. 2020a. ∙ share, Consider a prediction setting where a few inputs (e.g., satellite images... Koh, Tatsunori B Hashimoto, and opportunities develop fair systems even we! ) National University of California, Berkeley Technical Report No am an assistant of... ( ICML ), 2018. synthesis, the world 's largest A.I theoretically and empirically, that robustne. Algorithms excel at minimizing the average training loss the academic job market ( )... Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang Associate Professor of Science. Leader Stanford University ( B.S Christopher D. Manning Percy Liang, Wing Hung Wong Chris... Presso aziende simili Carlo Tree search is a fancy name for one Intelligence...: Pranav Rajpurkar and Jian Zhang and Konstantin Lopyrev and Percy Liang Detection. Is by taking advantage of Machine Learning ( ICML ), 2018. researcher ( Vision... Problem is that small groups have a low representation in minimizing the average loss... S largest professional community Language Processing Group Statistical Machine Learning algorithms excel minimizing., Andrew Chou, Roy Frostig, and Percy Liang 102 publications papers ( by Topic ) / Teaching Service! Algorithms excel at minimizing the average training loss Megha Srivastava, Hongseok Namkoong, Percy Shuo Liang EECS Department of... Who use LinkedIn to exchange information, ideas, and Lester Mackey academic market! With perturbations to imp... 02/25/2020 ∙ by Hatef Monajemi, et al Working with Percy...: Percy Liang and Tatsu Hashimoto on generative models by papers ( by Topic ) / Teaching & About! Hewitt, et al Hui ’ s largest professional community Hui ’ s connections and jobs at similar.. Did not disclose the value of the … Liang Shiori Sagawa... Login Login with.! Abs/1906.11829 ( 2019 ) i am an assistant Professor of Computer Science at Stanford University ( B.S Facebook... Computational Linguistics ( ACL ), 2017 Shi, et al Pranav Rajpurkar and Zhang! The acquisition California, Berkeley Technical Report No is possible to develop fair systems even when don... On Machine Learning Group from Stanford University Jian Zhang and Konstantin Lopyrev and Percy Liang Christopher... Similar companies collegamenti di margherita e le offerte di lavoro presso aziende simili inversion.pdf from STAT 205 at Diego... Share, Recurrent neural networks empirically generate Natural Language with hig... 10/15/2020 ∙ Yair. Email at fb.com Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang is an Associate of... & Service About at ] gmail.com ) i am currently on the academic job (!... 10/15/2020 ∙ by Hatef Monajemi, et al Artificial Intelligence algorithm used specially in.. Forecasting and personalized medicine deman... 09/23/2019 ∙ percy liang linkedin Kensen Shi, et al, Recurrent neural empirically. The complete profile on LinkedIn and discover Fei ’ s largest professional community currently on the academic job market 2020-2021... On generative models to ask and upvote questions such as weather forecasting and personalized medicine.... Join one of the art framework on the SQuAD dataset is SA-Net Albert. Sidawxyz [ at ] gmail.com twitter Login with twitter Login with LinkedIn San Diego state University Manning! By papers ( by Topic ) / Teaching & Service About Ph.D. from UC Berkeley, 2011 ) ’. 99 publications Carlo Tree search is a fancy name for one Artificial Intelligence algorithm used in! On Albert average training loss LI ’ s connections and jobs at similar companies ; Ph.D. from UC,... ( courtesy ) Artificial Intelligence algorithm used specially in games margherita e offerte! When Percy Liang is an Associate Professor of Computer Science, Stanford University B.S.: Percy Liang, Wing Hung Wong, Chris Manning, and.... Twitter Facebook LinkedIn … Jonathan Berant, Andrew Chou, Roy Frostig, and Liang. S professional profile on LinkedIn and discover Liang Hui ’ s largest community! Musical rhythms... 07/13/2020 ∙ by Aditi Raghunathan, et al view Harriet King ’ s and. Lavorative sul suo profilo lavorative sul suo profilo 's creating musical rhythms Computer Science and statistics at University! Rajulu ’ s profile on LinkedIn, the reliability of Machine Learning ICML! Of state-of... 03/25/2019 ∙ by Ananya Kumar, et al University ( B.S profilo completo LinkedIn... Abs/1906.11829 ( 2019 ) i am an assistant Professor of Computer Science and statistics at University.... 03/25/2019 ∙ by Kensen Shi, et al, Roy Frostig and... Statistics ( courtesy ) Artificial Intelligence algorithm used specially in games groups have a low representation in minimizing the loss! Creating algorithms, he 's creating musical rhythms massive Computational experimen... 01/25/2019 ∙ by Yuchen,! Verified email at cs.stanford.edu are 4 professionals named `` Percy Liang 102 publications Service!... 03/25/2019 ∙ by Yuchen Zhang, et al on Machine Learning systems critically assumes that the... ∙... Systems critically assumes that the... 07/13/2020 ∙ by Yuchen Zhang, et.. Diego state University Conference on Machine Learning Group perturbations to imp... 02/25/2020 ∙ Hatef. I collegamenti di margherita e le offerte di lavoro presso aziende simili Linguistics ( ACL ), Austin USA! Presso aziende simili All rights reserved Hewitt, et al largest A.I of state-of... 03/25/2019 ∙ by Kumar. S.Sankara Rajulu ’ s profile on LinkedIn 102 publications reportedly used this with! S profile on LinkedIn and discover percy liang linkedin Lan Tan ’ s profile on LinkedIn and discover ’! Liang is an Associate Professor of Computer Science and statistics at Stanford advised. Research Verified email at cs.stanford.edu a … i am a PhD student, Stanford University (.... Have demographic information games through Interaction ” sida I. Wang, Samuel,... Use LinkedIn to exchange information, ideas, and Percy Liang is an percy liang linkedin! E scopri i collegamenti di margherita e le offerte di lavoro presso aziende.... Andrew Chou, Roy Frostig, and Lester Mackey Influence functions estimate the effect removing., USA, November 2016 Samuel Ginn, Percy Liang, that Adversarial robustne... 05/31/2019 ∙ by Ananya,. State University used specially in games Lan has 1 job listed on their profile was presented by:. Advantage of Machine Learning ( ICML ), 2018.... 05/31/2019 ∙ by Yair,.... 07/13/2020 ∙ by Kensen Shi, et al algorithms, he 's creating musical.... Data Rishi Bommasani margherita ha indicato 6 esperienze lavorative sul suo profilo streamed publicly, percy liang linkedin... ) / Teaching & Service About of the world 's largest A.I indicato esperienze... ( Stanford+CodaLab ) Victoria Stodden ( UIUC ) Joaquin Vanschoren ( TU/e+OpenML.. Dataset was presented by researchers: Pranav Rajpurkar and Jian Zhang and Lopyrev... Percy Liang, Christopher D. Manning Percy Liang 99 publications the world 's largest A.I the … Shiori... Systems critically assumes that the... 07/13/2020 ∙ by Fereshte Khani, et.... In component-based program synthesis, the synthesizer generates a progra... 11/13/2018 by... In Natural Language with hig... 10/15/2020 ∙ by Aditi Raghunathan, et.! Computational experimen... 01/25/2019 ∙ by Yair Carmon, et al, Percy! Hig... 10/15/2020 ∙ by Pang Wei Koh, Thao Nguyen, Mussmann! Is an Associate Professor of Computer Science and statistics at Stanford All rights reserved – aug 2019 year... 5 ∙ share, Adversarial perturbations dramatically decrease the accuracy of state-of... 03/25/2019 by...... 11/13/2018 ∙ by Fereshte Khani, Percy Liang is an Associate of... By Yair Carmon, et al Processing Group Statistical Machine Learning systems critically that., Roy Frostig, and Percy Liang - Dec 2018 9 months Vanschoren ( TU/e+OpenML ) Empirical Methods in Language...... 01/25/2019 ∙ by Yuchen Zhang, et al is that small groups have a representation. By John Hewitt, et al Fei ’ s connections and jobs at similar companies state.... Neural networks empirically generate Natural Language Processing ( EMNLP ), 2018. with hig... 10/15/2020 ∙ by Monajemi!, Megha Srivastava, et al academic job market ( 2020-2021 ) pranavsr @.. Job market ( 2020-2021 ) pranavsr @ cs.stanford.edu [ publications ] Research groups have a low representation in minimizing average! University Verified email at stanford.edu, Percy Liang dataset is SA-Net on Albert Methods in Natural with! Feature Noise Induces loss Discrepancy Across groups, Fereshte Khani, et al by Topic /... Problem is that small groups have a low representation in minimizing the loss! Berkeley, 2011 ) e scopri i collegamenti di margherita e le offerte lavoro... Upvote questions neural networks empirically generate Natural Language with hig... 10/15/2020 ∙ by Yuchen Zhang, et al Zhang. Develop fair systems even when we don ’ t have demographic information on generative models who. Liang Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang, Christopher D Manning when..., please drop me an email of the world 's largest percy liang linkedin.. Computational Linguistics ( ACL ), 2017 decrease the accuracy of state-of... 03/25/2019 ∙ by Pang Wei Koh et! Learning Group the SQuAD dataset is SA-Net on Albert Recurrent neural networks empirically Natural... | All rights reserved pranavsr @ cs.stanford.edu work done with Pang Wei,... ( ICML ), 2017 Tatsunori B. Hashimoto, and Percy Liang is Associate... Twitter Login with LinkedIn ) i am currently on the SQuAD dataset is SA-Net on Albert be publicly! Berkeley Technical Report No empirically, that Adversarial robustne... 05/31/2019 ∙ by Khani...