Bio


Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. from MIT, 2004; Ph.D. from UC Berkeley, 2011). 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. 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).

Academic Appointments


Professional Education


  • BS, MIT (2004)
  • MEng, MIT (2005)
  • PhD, UC Berkeley (2011)

2020-21 Courses


Stanford Advisees


  • Doctoral Dissertation Reader (AC)
    Maxime Cauchois, Urvashi Khandelwal, Adam Lavertu, Zhengshan Shi
  • Postdoctoral Faculty Sponsor
    Chris Donahue
  • Doctoral Dissertation Advisor (AC)
    Steve Mussmann
  • Orals Evaluator
    Pranav Rajpurkar
  • Master's Program Advisor
    Prabhat Agarwal, Jonathan Li, Lucas Lin, Suvir Mirchandani, Claire Pajot, Chetanya Rastogi, Christopher Wolff, Sifan Ye, David Yin
  • Doctoral Dissertation Co-Advisor (AC)
    John Hewitt, Siddharth Karamcheti, Ananya Kumar, Daniel Levy, Pranav Rajpurkar
  • Doctoral (Program)
    Fereshte Khani, Pang Wei Koh, Mina Lee, Nelson Liu, Steve Mussmann, Aditi Raghunathan, Shiori Sagawa, Michael Xie, Michihiro Yasunaga

All Publications


  • Inferring Multidimensional Rates of Aging from Cross-Sectional Data. Proceedings of machine learning research Pierson, E., Koh, P. W., Hashimoto, T., Koller, D., Leskovec, J., Eriksson, N., Liang, P. 2019; 89: 97–107

    Abstract

    Modeling how individuals evolve over time is a fundamental problem in the natural and social sciences. However, existing datasets are often cross-sectional with each individual observed only once, making it impossible to apply traditional time-series methods. Motivated by the study of human aging, we present an interpretable latent-variable model that learns temporal dynamics from cross-sectional data. Our model represents each individual's features over time as a nonlinear function of a low-dimensional, linearly-evolving latent state. We prove that when this nonlinear function is constrained to be order-isomorphic, the model family is identifiable solely from cross-sectional data provided the distribution of time-independent variation is known. On the UK Biobank human health dataset, our model reconstructs the observed data while learning interpretable rates of aging associated with diseases, mortality, and aging risk factors.

    View details for PubMedID 31538144

  • Inferring Multidimensional Rates of Aging from Cross-Sectional Data Pierson, E., Koh, P., Hashimoto, T., Koller, D., Leskovec, J., Eriksson, N., Liang, P., Chaudhuri, K., Sugiyama, M. MICROTOME PUBLISHING. 2019: 97–107
  • Defending against Whitebox Adversarial Attacks via Randomized Discretization Zhang, Y., Liang, P., Chaudhuri, K., Sugiyama, M. MICROTOME PUBLISHING. 2019: 684–93
  • A Retrieve-and-Edit Framework for Predicting Structured Outputs Hashimoto, T. B., Guu, K., Oren, Y., Liang, P., Bengio, S., Wallach, H., Larochelle, H., Grauman, K., CesaBianchi, N., Garnett, R. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2018
  • Feature noising for log-linear structured prediction. Wang, S., Wang, M., Wager, S., Liang, P., Manning, C. 2013
  • A data driven approach for algebraic loop invariants. Sharma, R., Gupta, S., Hariharan, B., Aiken, A., Liang, P., Nori, Aditya, V. 2013
  • Spectral experts for estimating mixtures of linear regressions. Chaganty, A., Liang, P. 2013
  • Semantic parsing on Freebase from question-answer pairs. Berant, J., Chou, A., Frostig, R., Liang, P. 2013
  • Dropout training as adaptive regularization. Wager, S., Wang, S., Liang, P. 2013
  • Video event understanding using natural language descriptions. Ramanathan, V., Liang, P., Fei-Fei, L. 2013
  • Genome Editing of Human Embryonic Stem Cells and Induced Pluripotent Stem Cells With Zinc Finger Nucleases for Cellular Imaging CIRCULATION RESEARCH Wang, Y., Zhang, W. Y., Hu, S., Lan, F., Lee, A. S., Huber, B., Lisowski, L., Liang, P., Huang, M., de Almeida, P. E., Won, J. H., Sun, N., Robbins, R. C., Kay, M. A., Urnov, F. D., Wu, J. C. 2012; 111 (12): 1494-?

    Abstract

    Molecular imaging has proven to be a vital tool in the characterization of stem cell behavior in vivo. However, the integration of reporter genes has typically relied on random integration, a method that is associated with unwanted insertional mutagenesis and positional effects on transgene expression.To address this barrier, we used genome editing with zinc finger nuclease (ZFN) technology to integrate reporter genes into a safe harbor gene locus (PPP1R12C, also known as AAVS1) in the genome of human embryonic stem cells and human induced pluripotent stem cells for molecular imaging.We used ZFN technology to integrate a construct containing monomeric red fluorescent protein, firefly luciferase, and herpes simplex virus thymidine kinase reporter genes driven by a constitutive ubiquitin promoter into a safe harbor locus for fluorescence imaging, bioluminescence imaging, and positron emission tomography imaging, respectively. High efficiency of ZFN-mediated targeted integration was achieved in both human embryonic stem cells and induced pluripotent stem cells. ZFN-edited cells maintained both pluripotency and long-term reporter gene expression. Functionally, we successfully tracked the survival of ZFN-edited human embryonic stem cells and their differentiated cardiomyocytes and endothelial cells in murine models, demonstrating the use of ZFN-edited cells for preclinical studies in regenerative medicine.Our study demonstrates a novel application of ZFN technology to the targeted genetic engineering of human pluripotent stem cells and their progeny for molecular imaging in vitro and in vivo.

    View details for DOI 10.1161/CIRCRESAHA.112.274969

    View details for Web of Science ID 000311994700042

    View details for PubMedID 22967807

    View details for PubMedCentralID PMC3518748

  • Induced Pluripotent Stem Cells as a Disease Modeling and Drug Screening Platform JOURNAL OF CARDIOVASCULAR PHARMACOLOGY Ebert, A. D., Liang, P., Wu, J. C. 2012; 60 (4): 408-416

    Abstract

    Induced pluripotent stem cells (iPSCs) hold great hopes for therapeutic application in various diseases. Although ongoing research is dedicated to achieving clinical translation of iPSCs, further understanding of the mechanisms that underlie complex pathogenic conditions is required. Compared with other classical models for studying diseases, iPSCs provide considerable advantages. A newly emerging application of iPSCs is in vitro disease modeling, which can significantly improve the never-ending search for new pharmacological cures. Here, we will discuss current efforts to create iPSC-dependent patient-specific disease models. Furthermore, we will review the use of iPSCs for development and testing of new therapeutic agents and the implications for high-throughput drug screening.

    View details for DOI 10.1097/FJC.0b013e318247f642

    View details for Web of Science ID 000309977900012

    View details for PubMedID 22240913

    View details for PubMedCentralID PMC3343213

  • Modeling Pathogenesis in Familial Hypertrophic Cardiomyopathy Using Patient-Specific Induced Pluripotent Stem Cells Basic Cardiovascular Sciences Scientific Session Lan, F., Lee, A., Liang, P., Navarrete, E., Wang, L., Leng, H., Sanchez, V., Yen, M., Wang, Y., Nguyen, P., Sun, N., Abilez, O., Lewis, R., Yamaguchi, Y., Ashley, E., Bers, D., Robbins, R., Longaker, M., Wu, J. LIPPINCOTT WILLIAMS & WILKINS. 2012
  • Identifiability and unmixing of latent parse trees. Hsu, D., Kakade, Sham, M., Liang, P. 2012
  • Learning dependency-based compositional semantics. Liang, P., Jordan, Michael, I., Klein, D. 2011
  • Learning minimal abstractions. Liang, P., Tripp, O., Naik, M. 2011
  • Scaling up abstraction refinement via pruning. Liang, P., Naik, M. 2011
  • A dynamic evaluation of static heap abstractions. Liang, P., Tripp, O., Naik, M., Sagiv, M. 2010
  • Learning programs: a hierarchical Bayesian approach. Liang, P., Jordan, Michael, I., Klein, D. 2010
  • A game-theoretic approach to generating spatial descriptions. Golland, D., Liang, P., Klein, D. 2010
  • Type-based MCMC. Liang, P., Jordan, Michael, I., Klein, D. 2010
  • A simple domain-independent probabilistic approach to generation. Angeli, G., Liang, P., Klein, D. 2010
  • On the interaction between norm and dimensionality: multiple regimes in learning. Liang, P., Srebro, N. 2010
  • Learning from measurements in exponential families. Liang, P., Jordan, Michael, I., Klein, D. 2009
  • Learning semantic correspondences with less supervision. Liang, P., Jordan, Michael, I., Klein, D. 2009
  • Probabilistic grammars and hierarchical Dirichlet processes. The Oxford Handbook of Applied Bayesian Analysis Liang, P., Jordan, Michael, I., Klein, D. 2009
  • Online EM for unsupervised models. Liang, P., Klein, D. 2009
  • Asymptotically optimal regularization in smooth parametric models. Liang, P., Bach, F., Bouchard, G., Jordan, Michael, I. 2009
  • Optimal team size and monitoring in organizations ACCOUNTING REVIEW Liang, P. J., Rajan, M. V., Ray, K. 2008; 83 (3): 789-822
  • A probabilistic approach to language change. Bouchard-Côté, A., Liang, P., Griffiths, T., Klein, D. 2008
  • Agreement-based learning. Liang, P., Klein, D., Jordan, Michael, I. 2008
  • Learning bilingual lexicons from monolingual corpora. Haghighi, A., Liang, P., Berg-Kirkpatrick, T., Klein, D. 2008
  • Structure compilation: trading structure for features. Liang, P., Daume, H., Klein, D. 2008
  • Analyzing the errors of unsupervised learning. Liang, P., Klein, D. 2008
  • An asymptotic analysis of generative, discriminative, and pseudolikelihood estimators. Liang, P., Jordan, Michael, I. 2008
  • A probabilistic approach to diachronic phonology. Bouchard-Côté, A., Liang, P., Griffiths, T., Klein, D. 2007
  • A permutation-augmented sampler for Dirichlet process mixture models. Liang, P., Jordan, Michael, I., Taskar, B. 2007
  • Structured Bayesian nonparametric models with variational inference (tutorial). Liang, P., Klein, D. 2007
  • The infinite PCFG using hierarchical Dirichlet processes. Liang, P., Petrov, S., Jordan, Michael, I., Klein, D. 2007
  • An end-to-end discriminative approach to machine translation. Liang, P., Bouchard-Côté, A., Klein, D., Taskar, B. 2006
  • Alignment by agreement. Liang, P., Taskar, B., Klein, D. 2006
  • Linear programming in bounded tree-width Markov networks. Liang, P., Srebro, N. 2005
  • A data structure for maintaining acyclicity in hypergraphs. Massachusetts Institute of Technology Technical Report Liang, P., Srebro, N. 2005
  • Efficient geometric algorithms for parsing in two dimensions. Liang, P., Narasimhan, M., Shilman, M., Viola, P. 2005
  • Methods and experiments with bounded tree-width Markov networks. Massachusetts Institute of Technology Technical Report Liang, P., Srebro, N. 2004
  • How much of a hypertree can be captured by windmills? Massachusetts Institute of Technology Technical Report Liang, P., Srebro, N. 2003
  • INTERFEROMETRIC STUDIES OF THE JOVIAN ATMOSPHERIC PROBE FIELD Liang, P. Y., Prakash, S. G., Bershader, D. AMER INST PHYSICS. 1980: 1093–94
  • Saponins and sapogenins. III. The sapogenins obtained from chlorogalum pomeridianum JOURNAL OF THE AMERICAN CHEMICAL SOCIETY Liang, P., Noller, C. R. 1935; 57 (1): 525-527