Paul Pu Liang, CMU

Paul Pu Liang

Email: pliang(at)
Office: Gates and Hillman Center 8011
5000 Forbes Avenue, Pittsburgh, PA 15213
Multicomp Lab, Language Technologies Institute, School of Computer Science, Carnegie Mellon University
[CV] @pliang279 @lpwinniethepu

I am a first year Ph.D. student in the Machine Learning Department at CMU, advised by Louis-Philippe Morency and Ruslan Salakhutdinov. My research is centered around multimodal machine learning, deep learning, semi-supervised learning, and unsupervised learning. I apply these methods to problems in natural language processing, computer vision, speech processing, and reinforcement learning. I received an M.S. in Machine Learning and a B.S. with University Honors in Computer Science from CMU, where I was extremely fortunate to have worked with Louis-Philippe Morency, Ruslan Salakhutdinov, Roni Rosenfeld, Barnabás Poczós and Tai Sing Lee. I have also spent time as a research intern at Google Research and RIKEN Artificial Intelligence Project.



Work Experience


(* denotes joint first-authors)


  1. Think Locally, Act Globally: Federated Learning with Local and Global Representations
  2. Paul Pu Liang*, Terrance Liu*, Ziyin Liu, Ruslan Salakhutdinov, Louis-Philippe Morency
    arXiv 2019
    [paper] [arXiv]
  3. Deep Gamblers: Learning to Abstain with Portfolio Theory
  4. Ziyin Liu, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda
    arXiv 2019
    [paper] [arXiv]
  5. Variational Auto-Decoder: Neural Generative Modeling from Incomplete Data
  6. Amir Zadeh, Yao Chong Lim, Paul Pu Liang, Louis-Philippe Morency
    arXiv 2019
    [paper] [arXiv] [code]
  7. Hierarchical Seq2Seq: Learning Representations of Online Spoken Speech
  8. Irene Li, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    arXiv 2019
    [paper] [arXiv] [code]
  9. Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
  10. Paul Pu Liang*, Zhun Liu*, Yao-Hung Hubert Tsai, Qibin Zhao, Ruslan Salakhutdinov, Louis-Philippe Morency
    ACL 2019
    [paper] [arXiv]
  11. Multimodal Transformer for Unaligned Multimodal Language Sequences
  12. Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov
    ACL 2019
    [paper] [arXiv] [code]
  13. Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence
  14. Amir Zadeh, Michael Chan, Paul Pu Liang, Edmund Tong, Louis-Philippe Morency
    CVPR 2019 (oral)
    [paper] [arXiv] [code] [slides] [poster]
  15. Strong and Simple Baselines for Multimodal Utterance Embeddings
  16. Paul Pu Liang*, Yao Chong Lim*, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Louis-Philippe Morency
    NAACL 2019 (oral)
    [paper] [arXiv] [code] [slides]
  17. Learning Factorized Multimodal Representations
  18. Paul Pu Liang*, Yao-Hung Hubert Tsai*, Amir Zadeh, Louis-Philippe Morency, Ruslan Salakhutdinov
    ICLR 2019
    NeurIPS 2018 Workshop on Bayesian Deep Learning
    [paper] [arXiv] [code] [poster]
  19. Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities
  20. Paul Pu Liang*, Hai Pham*, Thomas Manzini, Louis-Philippe Morency, Barnabás Póczos
    AAAI 2019
    NeurIPS 2018 Workshop on Interpretability and Robustness in Audio, Speech and Language (oral)
    [paper] [arXiv] [code] [slides] [poster]
  21. Words can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors
  22. Yansen Wang, Ying Shen, Zhun Liu, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    AAAI 2019
    [paper] [arXiv] [code] [slides] [poster]


  1. Computational Modeling of Human Multimodal Language: The MOSEI Dataset and Interpretable Dynamic Fusion
  2. Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency
    Master's Thesis, CMU Machine Learning Data Analysis Project 2018 (best presentation runner-up)
    [paper] [slides] [poster]
  3. Multimodal Language Analysis with Recurrent Multistage Fusion
  4. Paul Pu Liang, Ziyin Liu, Amir Zadeh, Louis-Philippe Morency
    EMNLP 2018 (oral)
    NeurIPS 2018 Workshop on Modeling and Decision-making in the Spatiotemporal Domain (oral)
    [paper] [arXiv] [slides] [poster]
  5. Multimodal Local-Global Ranking Fusion for Emotion Recognition
  6. Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    ICMI 2018
    [paper] [arXiv] [poster]
  7. An Empirical Evaluation of Sketched SVD and its Application to Leverage Score Ordering
  8. Hui Han Chin, Paul Pu Liang
    ACML 2018
    [paper] [arXiv] [slides] [poster]
  9. Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
  10. Amir Zadeh, Paul Pu Liang, Jonathan Vanbriesen, Soujanya Poria, Edmund Tong, Erik Cambria, Minghai Chen, Louis-Philippe Morency
    ACL 2018 (oral)
    [paper] [arXiv] [slides] [code]
  11. Efficient Low-rank Multimodal Fusion with Modality-Specific Factors
  12. Zhun Liu, Ying Shen, Varun Lakshminarasimhan, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    ACL 2018 (oral)
    [paper] [arXiv] [slides] [code]
  13. Proceedings of the First Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML)
  14. Amir Zadeh, Paul Pu Liang, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer
    ACL 2018 Workshop Proceedings
    [proceedings] [website] [introduction] [datasets] [results]
  15. Multi-attention Recurrent Network for Human Communication Comprehension
  16. Amir Zadeh, Paul Pu Liang, Soujanya Poria, Prateek Vij, Erik Cambria, Louis-Philippe Morency
    AAAI 2018 (oral)
    [paper] [arXiv] [slides] [code]
  17. Memory Fusion Network for Multi-view Sequential Learning
  18. Amir Zadeh, Paul Pu Liang, Navonil Mazumder, Soujanya Poria, Erik Cambria, Louis-Philippe Morency
    AAAI 2018 (oral)
    [paper] [arXiv] [slides] [code]


  1. Multimodal Sentiment Analysis with Word-level Fusion and Reinforcement Learning
  2. Paul Pu Liang*, Minghai Chen*, Sen Wang*, Tadas Baltrušaitis, Amir Zadeh, Louis-Philippe Morency
    ICMI 2017 (oral, honorable mention award)
    [paper] [arXiv] [slides]



Academic Talks

Professional Activities

I have an Erdős number of 3 (Paul Erdős → Giuseppe Melfi → Erik Cambria → Paul Pu Liang).
This page has been accessed at least several times since Feb 8, 2018.