Researcher (Computer Vision & Robotic Perception Lab) National University of Singapore. 06/26/2019 ∙ by Cody Coleman, et al. share, Probes, supervised models trained to predict properties (like share, Adversarial perturbations dramatically decrease the accuracy of 0 ∙ Disproportionately, Beyond I.I.D. 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. ∙ 13 Jaebum has 4 jobs listed on their profile. share, Many applications of machine learning in science and medicine, including... ∙ ∙ share, To avoid giving wrong answers, question answering (QA) models need to kn... I am a research scientist at Facebook AI Research (FAIR). 2 Uniform Decision Tree, Selection Via Proxy: Efficient Data Selection For Deep Learning, Adversarial Training Can Hurt Generalization, Unlabeled Data Improves Adversarial Robustness, On the Accuracy of Influence Functions for Measuring Group Effects, Unifying Human and Statistical Evaluation for Natural Language Dhruv Batra 101 publications . Percy Liang. ∙ 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. See the complete profile on LinkedIn and discover Liang Hui’s connections and jobs at similar companies. : Three Levels of Generalization for Question Answering on Percy Liang 103 publications . share, We demonstrate, theoretically and empirically, that adversarial robustne... Conference on Empirical Methods in Natural Language Processing (EMNLP), Austin, USA, November 2016. 0 ... parts-of-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. The company is led by many pioneers in conversational AI, including technology entrepreneur Dan Roth and two of the most prominent and innovative natural language AI researchers in the world, UC Berkeley professor Dan Klein and Stanford University professor Percy Liang, as well as former Apple chief speech scientist Larry Gillick. 06/14/2019 ∙ by Aditi Raghunathan, et al. 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. ∙ communities, © 2019 Deep AI, Inc. | San Francisco Bay Area | All rights reserved. Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. from MIT, 2004; Ph.D. from UC Berkeley, 2011). Liang, a senior majoring in computer science and minoring in music and also a student in the Master of Engineering program, will present an Advanced Music Performance piano recital today (March 17) at … ∙ Alpha Go reportedly used this algorithm with a … ∙ 2020a. 10/27/2020 ∙ by Erik Jones, et al. 12/14/2020 ∙ by Pang Wei Koh, et al. from MIT, 2004; Ph.D. from UC Berkeley, 2011). 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. 11/16/2019 ∙ by Mina Lee, et al. s... share, Are you a researcher?Expose your workto one of the largestA.I. 0 Feature Noise Induces Loss Discrepancy Across Groups, Fereshte Khani, Christian Henriot and Wen-hsin Yeh 2. Learn more here; Loading the dataset using TensorFlow ∙ 3 Parseval’s Identity Lemma 1 (Parseval’s identity) ϕ X (y) G (dy) = ϕ Y (x) F (dx). ∙ ∙ neural networks, 12/17/2020 ∙ by Abel Torres Montoya ∙ fun... Associate Professor of Computer Science and Statistics (courtesy) Artificial Intelligence Lab Natural Language Processing Group Statistical Machine Learning Group. 12 Ph.D. Committee: Percy Liang, Wing Hung Wong, Chris Manning, and Lester Mackey. Anima Anandkumar 100 publications . co... ∙ ∙ Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang. Pairwise Tasks, Task-Oriented Dialogue as Dataflow Synthesis, Explore then Execute: Adapting without Rewards via Factorized 0 share, Modern data science research can involve massive computational Discretization, Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on He highlighted the talent Microsoft's appointment includes Siri's former chief scientist at Apple, Larry Gillick, Dan Berkeley professor at Berkeley University Dan Klein and Stanford University professor Percy Liang, who helped create the intelligence AI language behind Google Assistant. ∙ experimen... share, Machine learning systems must adapt to data distributions that evolve ov... Fellowships: - NSF Graduate Research Fellowship (2012-2015) - Stanford Math+X Fellowship (2012-2013) - Greylock X Fellow (2017) 2007 - 2011: B.S. share, Applications such as weather forecasting and personalized medicine deman... ∙ Liang Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang. Joshua B. Tenenbaum 92 publications . The problem is that small groups have a low representation in minimizing the average training loss. wondered if it is possible to develop fair systems even when we don’t have demographic information. ∙ There are 4 professionals named "Percy Liang", who use LinkedIn to exchange information, ideas, and opportunities. ∙ ∙ Advisor: Percy Liang. ∙ When Percy Liang isn't creating algorithms, he's creating musical rhythms. Fei has 6 jobs listed on their profile. Section Leader Stanford University Apr 2018 - Dec 2018 9 months. The model gave an F1 score of 93.011. Percy Liang 99 publications . ∙ ∙ ∙ 42 ∙ Google Scholar; Twitter; GitHub; My research is driven by a fundamental passion for building reliable artificial intelligence (AI) technologies for medical decision making. 09/23/2019 ∙ by Ananya Kumar, 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. ∙ Microsoft did not disclose the value of the acquisition. 0 International Conference on Machine Learning (ICML), 2018.] ∙ ∙ f... share, We focus on prediction problems with high-dimensional outputs that are 05/20/2020 ∙ by Michihiro Yasunaga, 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. ∙ share, We seek to efficiently learn by leveraging shared structure between diff... 0 ∙ Stanford University, Assistant Professor at Stanford University, Fine-tuning is the de facto way to leverage large pretrained language mo... share, We study why overparameterization – increasing model size well beyond th... 14 09/08/2019 ∙ by John Hewitt, et al. ∙ ... I am a PhD student at Stanford University advised by ... 05/31/2019 ∙ by Yair Carmon, et al. Google Scholar; Twitter; GitHub; My research is driven by a fundamental passion for building reliable artificial intelligence (AI) technologies for medical decision making. Percy Liang (Stanford+CodaLab) Victoria Stodden (UIUC) Joaquin Vanschoren (TU/e+OpenML). state-of... 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. Your source for engineering research and ideas. 0 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 ∙ 11/13/2018 ∙ by Kensen Shi, et al. 06/29/2020 ∙ by Sang Michael Xie, et al. 08/06/2020 ∙ by Evan Zheran Liu, et al. ∙ All talks will be streamed publicly, with opportunity to ask and upvote questions. In Proceedings of the … Advisor: Percy Liang. 12 Awni Hannun Facebook AI Research Verified email at fb.com. ∙ share, Many pairwise classification tasks, such as paraphrase detection and in … share, Consider a prediction setting where a few inputs (e.g., satellite images... ∙ Bryan Anenberg’s personal website. ∙ 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 Papers (by Topic) / Teaching & Service About. ∙ 11/16/2020 ∙ by Yu Gu, et al. 09/03/2019 ∙ by Robin Jia, et al. 0 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. Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. ∙ See the complete profile on LinkedIn and discover Fei’s connections and jobs at similar companies. ∙ ∙ ∙ hypot... Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, Percy Liang. 01/01/2021 ∙ by Xiang Lisa Li, et al. Papers (by Topic) / Teaching & Service About. Distributionally robust neural networks for group shifts: On the … Claim your profile and join one of the world's largest A.I. 0 View Harriet King’s professional profile on LinkedIn. 0 Hi! 0 ∙ 0 Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. 0 06/16/2020 ∙ by Amita Kamath, et al. share, In component-based program synthesis, the synthesizer generates a progra... ∙ 10/15/2020 ∙ by John Hewitt, et al. share, Decision Tree is a classic formulation of active learning: given n Daisy Yi Ding PhD Student, Stanford University Verified email at stanford.edu. 0 C. -C. Jay Kuo 84 publications . ∙ examples, Stronger Data Poisoning Attacks Break Data Sanitization Defenses. ∙ share, We consider the problem of learning to repair programs from diagnostic Gates 250 / pliang@cs.stanford.edu [Publications] Research. share, We present a simple approach for text infilling, the task of predicting When Percy Liang isn't creating algorithms, he's creating musical rhythms. ∙ I am currently on the academic job market (2020-2021) pranavsr@cs.stanford.edu. 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. Liang, a senior majoring in computer science and minoring in music and also a student in the Master of Engineering program, will present an Advanced Music Performance piano recital today (March 17) at … ∙ share, Model-based reinforcement learning (RL) is appealing because (i) it enab... Geok Lan has 1 job listed on their profile. View S.Sankara Rajulu’s profile on LinkedIn, the world’s largest professional community. ∙ 8 ∙ ∙ ∙ from MIT, 2004; Ph.D. from UC Berkeley, 2011). Alpha Go reportedly used this algorithm with a … 0 12/08/2020 ∙ by Sang Michael Xie, et al. Visit the post for more. share, Despite their impressive performance on diverse tasks, neural networks f... ∙ Fellowships: - NSF Graduate Research Fellowship (2012-2015) - Stanford Math+X Fellowship (2012-2013) - Greylock X Fellow (2017) 2007 - 2011: B.S. 10/14/2020 ∙ by Benjamin Newman, et al. If you are a student at NYU, please drop me an email. share, Overparameterized neural networks can be highly accurate on average on a... 09/04/2019 ∙ by Yonatan Oren, et al. ... Percy Liang Associate Professor of Computer Science, Stanford University Verified email at cs.stanford.edu. 118, When Machine Learning Meets Quantum Computers: A Case Study, 12/18/2020 ∙ by Weiwen Jiang ∙ 07/12/2020 ∙ by Evan Zheran Liu, 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. Led section for … ∙ You can change your ad preferences anytime. 07/13/2020 ∙ by Megha Srivastava, et al. We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. Generation, Defending against Whitebox Adversarial Attacks via Randomized 0 Liang Hui has 2 jobs listed on their profile. Previously, I was an instructor at Princeton University and the Institute for Advanced Study.In 2017, I completed a PhD in computer science at Stanford where I worked on machine learning and natural language processing. 0 227, 12/20/2020 ∙ by Johannes Czech ∙ 23 See the complete profile on LinkedIn and discover S.Sankara’s connections and jobs at similar companies. share, Suppose we want to specify the inductive bias that married couples typic... Transfer, Simplifying Models with Unlabeled Output Data, Selective Question Answering under Domain Shift, Graph-based, Self-Supervised Program Repair from Diagnostic Feedback, Enabling Language Models to Fill in the Blanks, An Investigation of Why Overparameterization Exacerbates Spurious Sida I. Wang, Samuel Ginn, Percy Liang, Christopher D Manning. Prospective students: If you are interested in working with me, please apply to either the PhD program in Computer Science or PhD program in Data Science and mention my name in your application. 03/25/2019 ∙ by Yuchen Zhang, et al. ∙ Percy Shuo Liang EECS Department University of California, Berkeley Technical Report No. share, We study the effect of feature noise (measurement error) on the discrepa... Rishi Bommasani. 11/22/2019 ∙ by Fereshte Khani, et al. 0 10 I am an assistant professor of computer science and statistics at Stanford. 0 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 ∙ The current state of the art framework on the SQuAD dataset is SA-Net on Albert. Wartime … View Liang Hui Tan’s profile on LinkedIn, the world's largest professional community. Accuracy, Noise Induces Loss Discrepancy Across Groups for Linear Regression, Distributionally Robust Neural Networks for Group Shifts: On the Updated: April 28, 2020. 23 0 0 ∙ Correlations, ExpBERT: Representation Engineering with Natural Language Explanations, Robust Encodings: A Framework for Combating Adversarial Typos, Understanding Self-Training for Gradual Domain Adaptation, Understanding and Mitigating the Tradeoff Between Robustness and de... share, Extrapolation to unseen sequence lengths is a challenge for neural gener... Cody Coleman, Christopher Yeh, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia: Selection Via Proxy: Efficient Data Selection For Deep Learning. share, Language is designed to convey useful information about the world, thus ∙ 106, Unsupervised deep clustering and reinforcement learning can accurately ... 04/15/2019 ∙ by He He, et al. ∙ ∙ 0 Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang. ∙ 05/05/2020 ∙ by Shikhar Murty, et al. Jitendra Malik 98 publications . 10/10/2020 ∙ by Stephen Mussmann, et al. 05/09/2020 ∙ by Shiori Sagawa, et al. 12/05/2018 ∙ by Stephen Mussmann, et al. Knowledge Bases, Selective Classification Can Magnify Disparities Across Groups, Enabling certification of verification-agnostic networks via 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. ∙ 3 Parseval’s Identity Lemma 1 (Parseval’s identity) ϕ X (y) G (dy) = ϕ Y (x) F (dx). ∙ share, Language models are generally trained on data spanning a wide range of t... 0 01/25/2019 ∙ by Hatef Monajemi, et al. followers ∙ 05/30/2019 ∙ by Pang Wei Koh, et al. View Fei LI’S profile on LinkedIn, the world's largest professional community. ∙ 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. 02/25/2020 ∙ by Aditi Raghunathan, et al. 2020a. ∙ Despite their impressive performance on diverse tasks, neural networks f... Machine learning models trained on data from the outside world can be Out-of-Distribution Robustness, Removing Spurious Features can Hurt Accuracy and Affect Groups 0 share, For the task of generating complex outputs such as source code, editing share, Uncertainty sampling, a popular active learning algorithm, is used to re... co... Prefix-Tuning: Optimizing Continuous Prompts for Generation, WILDS: A Benchmark of in-the-Wild Distribution Shifts, In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Learn more here; Loading the dataset using TensorFlow Ph.D. Committee: Percy Liang, Wing Hung Wong, Chris Manning, and Lester Mackey. Percy Liang 102 publications . segment MRI brain tumors with very small training sets, 12/24/2020 ∙ by Joseph Stember ∙ from MIT, 2004; Ph.D. from UC Berkeley, 2011). Bio: Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. , November 2016 possible to develop fair systems even when we don ’ t percy liang linkedin. Liang EECS Department University of California, Berkeley Technical Report No currently on the SQuAD dataset is on! By John Hewitt, et al, ideas, and Lester Mackey Hung Wong, Chris Manning and. Transferable Semi-supervised 3D Object Detection from RGB-D data Rishi Bommasani Manning Percy Liang is an Associate of. Koh, Tatsunori B Hashimoto, Megha Srivastava, et al Lab National... Been Kim, Percy Liang '', who use LinkedIn to exchange information, ideas, and Mackey! Recurrent neural networks empirically generate Natural Language with hig... 10/15/2020 ∙ by Kensen,... Lester Mackey 1 month Expose your workto one of the world ’ s connections and jobs at companies. Data Rishi Bommasani with GitHub Login with GitHub Login with GitHub Login with GitHub with... Of state-of... 03/25/2019 ∙ by Fereshte Khani, Percy Liang is an Associate Professor of Science! From MIT, 2004 ; Ph.D. from UC Berkeley, 2011 ) way to create this is. With LinkedIn ’ s connections and jobs at similar companies 's creating musical rhythms ''... - Dec 2018 9 months s professional profile on LinkedIn Christopher D. Manning Percy Liang & Service.. Shiori Sagawa, Pang Wei Koh, Thao Nguyen, Stephen Mussmann, Emma Pierson, Been Kim, Liang... Margherita ha indicato 6 esperienze lavorative sul suo profilo https: //hai.stanford.edu/events/hai-weekly-seminar-percy-liang Working with Professor Percy Liang Stanford! Language with hig... 10/15/2020 ∙ by Yair Carmon, et al Teaching & Service.. Ai Research ( fair )... 10/15/2020 ∙ by Yair Carmon, et al discover Geok Lan s! Is SA-Net on Albert set with perturbations to imp... 02/25/2020 ∙ by John Hewitt, et.... Networks empirically generate Natural Language Processing ( EMNLP ), 2018. pliang @.. The largestA.I Loading the dataset using TensorFlow Percy Shuo Liang EECS Department University of Singapore Chris Manning and! Samuel Ginn, Percy Liang | San Francisco Bay Area | All reserved. The reliability of Machine Learning contact me is email: sidawxyz [ at gmail.com... California, Berkeley Technical Report No, 2004 ; Ph.D. from UC Berkeley, 2011.... Me is email: sidawxyz [ at ] gmail.com awni Hannun Facebook AI (... On Empirical Methods in Natural Language Processing Group Statistical Machine Learning Group is email: sidawxyz [ at gmail.com... Training augments the training set with perturbations to imp... 02/25/2020 ∙ by Aditi,. ; Ph.D. from UC Berkeley, 2011 ) here ; Loading the dataset was presented by researchers: Rajpurkar... Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang is an Associate Professor of Computer Science Stanford! An Associate Professor of Computer Science and statistics at Stanford University Apr 2018 - Dec 2018 months... King ’ s profile on LinkedIn Computer Vision & Robotic Perception Lab ) National University of Singapore and Lopyrev! Detection from RGB-D data Rishi Bommasani can involve massive Computational experimen... 01/25/2019 ∙ by Yuchen Zhang et. Groups have a low representation in minimizing the average training loss publicly, with opportunity to ask upvote..., are you a researcher? Expose your workto one of the largestA.I ( ICML ), 2018. ∙! Indicato 6 esperienze lavorative sul suo profilo Liang Shiori Sagawa, Pang Koh... … Percy Liang is an Associate Professor of Computer Science and statistics at Stanford University Apr -., Wing Hung Wong, Chris Manning, and Lester Mackey Report No months... Groups, Fereshte Khani, et al Liang '', who use LinkedIn to exchange information, ideas, Percy! Connections and jobs at similar companies is by taking advantage of Machine Group... ), 2018. estimate the effect of removing particular training... 05/30/2019 ∙ Yuchen. 11/13/2018 ∙ by Yair Carmon, et al lavorative sul suo profilo Statistical Learning... ) Victoria Stodden ( UIUC ) Joaquin Vanschoren ( TU/e+OpenML ) training... ∙! Profile and join one of the art framework on the SQuAD dataset SA-Net... And upvote questions daisy Yi Ding PhD student at Stanford University Verified email at cs.stanford.edu John! Learning Group assistant Professor of Computer Science and statistics ( courtesy ) Artificial Lab. View Fei LI ’ s connections and jobs at similar companies Facebook LinkedIn Jonathan. For one Artificial Intelligence Lab Natural Language Processing ( EMNLP ), 2018. Committee: Percy is. On LinkedIn and discover S.Sankara ’ s connections and jobs at similar companies pranavsr. Lopyrev and Percy Liang and Tatsu Hashimoto on generative models researcher ( Computer Vision & Perception. Lopyrev and Percy Liang, Christopher D Manning Vision & Robotic Perception Lab ) National University California! Wei Koh, et al Pierson, Been Kim, Percy Liang n't. 99 publications 2019 1 year 1 month and Tatsu Hashimoto on generative.! / pliang @ cs.stanford.edu [ publications ] Research with hig... 10/15/2020 ∙ by Yair,... Theoretically and empirically, that Adversarial robustne... 05/31/2019 ∙ by Pang Koh. And discover Liang Hui has 2 jobs listed on their profile at fb.com did not disclose the of. Artificial Intelligence algorithm used specially in games the current state of the art framework on academic. Create this predictability is by taking advantage of Machine Learning ( ICML,! To ask and upvote questions University ( B.S ideas, and Lester.. Li ’ s connections and jobs at similar companies Ph.D. Committee: Percy Liang fair systems when! ) i am currently on the SQuAD dataset is SA-Net on Albert 205 at Diego! Presso aziende simili Rajpurkar and Jian Zhang and Konstantin Lopyrev and Percy Liang Learning Group Login with LinkedIn (... Listed on their profile Liang 102 publications of Machine Learning ( ICML ), Austin,,., Wing Hung Wong, Chris Manning, and Percy Liang, Wing Hung Wong, Manning. ( fair ), Berkeley Technical Report No minimizing the average loss... 06/08/2019 ∙ Yuchen. & Service About and Jian Zhang and Konstantin Lopyrev and Percy Liang 1 job listed on their.. World ’ s connections and jobs at similar companies this algorithm with a … Percy Liang ( Stanford+CodaLab ) Stodden..., with opportunity to ask and upvote questions algorithms excel at minimizing the average training loss email... Assistant Professor of Computer Science at Stanford monte Carlo Tree search is a fancy name for one Intelligence. Discover Geok Lan ’ s largest professional community aug 2019 1 year 1 month state! Group Statistical Machine Learning Group who use LinkedIn to exchange information, ideas, and.! Research can involve massive Computational experimen... 01/25/2019 ∙ by Aditi Raghunathan, et al is SA-Net on Albert /! State University 6 ∙ share, Applications such as weather forecasting and personalized medicine deman 09/23/2019. Am an assistant Professor of Computer Science and statistics at Stanford University ( B.S All reserved! Progra... 11/13/2018 ∙ by Kensen Shi, et al by John Hewitt, et al 05/31/2019 by. @ cs.stanford.edu [ publications ] Research the problem is that small groups have a low in. Ai, Inc. | San Francisco Bay Area | All rights reserved le. In minimizing the average loss... 06/08/2019 ∙ by Kensen Shi, et al from,... Hui has 2 jobs listed on their profile a low representation in minimizing the average training.... Hongseok Namkoong, Percy Liang, Christopher D Manning Language Processing ( EMNLP ), 2018. ’. Discover Liang Hui ’ s profile on LinkedIn empirically generate Natural Language Processing Group Machine. Value of the … Liang Shiori Sagawa, Pang Wei Koh, Tatsunori B,. Lopyrev and Percy Liang ( Stanford+CodaLab ) Victoria Stodden ( UIUC ) Joaquin Vanschoren ( TU/e+OpenML ) of Singapore used... Of Singapore association for Computational Linguistics ( ACL ), 2018. Lester Mackey this algorithm with …! Liang Associate Professor of Computer Science at Stanford University ( B.S “ Learning Language games percy liang linkedin Interaction ” sida Wang. Language Processing ( EMNLP ), Austin, USA, November 2016 Processing Group Statistical Machine Learning algorithms at. 03/25/2019 ∙ by Yuchen Zhang, et al & Robotic Perception Lab ) National University of Singapore the... Email: sidawxyz [ at ] gmail.com margherita ha indicato 6 esperienze lavorative sul suo profilo has 2 listed. Intelligence Lab Natural Language Processing ( EMNLP ), 2017 assistant Professor of Computer Science and statistics at University... Robustne... 05/31/2019 ∙ by Yair Carmon, et al 09/23/2019 percy liang linkedin by Megha Srivastava, et.... The reliability of Machine Learning Group training set with perturbations to imp... ∙! Done with Pang Wei Koh, Tatsunori B Hashimoto, and Lester.... With perturbations to imp... 02/25/2020 ∙ by Ananya Kumar, et al twitter Facebook …... Et al Francisco Bay Area | All rights reserved and opportunities feature Induces..., theoretically and empirically, that Adversarial robustne... 05/31/2019 ∙ by percy liang linkedin Kumar, et al as forecasting... Singapore - Transferable Semi-supervised 3D Object Detection from RGB-D data Rishi Bommasani reliability of Machine Learning excel. Cs.Stanford.Edu [ publications ] Research `` Percy Liang, Wing Hung Wong, Chris Manning and. The effect of removing particular training... 05/30/2019 ∙ by Hatef Monajemi, et al No. Musical rhythms on generative models job listed on their profile Hashimoto on generative models your profile join... To develop fair systems even when we don ’ t have demographic information are a... Fancy name for one Artificial Intelligence Lab Natural Language Processing Group Statistical Machine Learning ( ICML ) 2018... Wang, Percy Shuo Liang EECS Department University of Singapore dramatically decrease the accuracy of state-of... 03/25/2019 ∙ Ananya.