Paul Pu Liang, CMU

Paul Pu Liang

Email: pliang(at)cs.cmu.edu
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


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. From the applications perspective, I am interested in natural language processing, computer vision, 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.

News

Education

Publications

2019

  1. Learning Factorized Multimodal Representations
  2. Paul Pu Liang*, Yao-Hung Hubert Tsai*, Amir Zadeh, Louis-Philippe Morency, Ruslan Salakhutdinov (*equal contributions)
    ICLR 2019
    [paper] [arXiv] [poster]
  3. Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities
  4. Paul Pu Liang*, Hai Pham*, Thomas Manzini, Louis-Philippe Morency, Barnabás Póczos (*equal contributions)
    AAAI 2019
    [paper] [supp] [arXiv] [poster]
  5. Words can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors
  6. Yansen Wang, Ying Shen, Zhun Liu, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    AAAI 2019
    [paper] [arXiv] [code] [poster]

2018

  1. Learning Robust Joint Representations for Multimodal Sentiment Analysis
  2. Paul Pu Liang*, Hai Pham*, Thomas Manzini, Louis-Philippe Morency, Barnabás Póczos (*equal contributions)
    NeurIPS 2018 Workshop on Interpretability and Robustness in Audio, Speech and Language (oral presentation)
    [paper] [arXiv] [slides]
  3. Modeling Spatiotemporal Multimodal Language with Recurrent Multistage Fusion
  4. Paul Pu Liang, Ziyin Liu, Amir Zadeh, Louis-Philippe Morency
    NeurIPS 2018 Workshop on Modeling and Decision-making in the Spatiotemporal Domain (oral presentation)
    [paper] [arXiv] [slides] [poster]
  5. Learning Multimodal Representations with Factorized Deep Generative Models
  6. Paul Pu Liang*, Yao-Hung Hubert Tsai*, Amir Zadeh, Louis-Philippe Morency, Ruslan Salakhutdinov (*equal contributions)
    NeurIPS 2018 Workshop on Bayesian Deep Learning
    [paper] [arXiv] [poster]
  7. Relational Attention Networks via Fully-Connected Conditional Random Fields
  8. Ziyin Liu, Junxiang Chen, Paul Pu Liang, Masahito Ueda
    NeurIPS 2018 Workshop on Bayesian Deep Learning
    [paper] [poster]
  9. Computational Modeling of Human Multimodal Language: The MOSEI Dataset and Interpretable Dynamic Fusion
  10. 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]
  11. Multimodal Language Analysis with Recurrent Multistage Fusion
  12. Paul Pu Liang, Ziyin Liu, Amir Zadeh, Louis-Philippe Morency
    EMNLP 2018 (oral presentation)
    [paper] [supp] [arXiv] [slides]
  13. An Empirical Evaluation of Sketched SVD and its Application to Leverage Score Ordering
  14. with Hui Han Chin (alphabetical ordering)
    ACML 2018
    [paper] [arXiv] [slides] [poster]
  15. Multimodal Local-Global Ranking Fusion for Emotion Recognition
  16. Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    ICMI 2018
    [paper] [arXiv] [poster]
  17. Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
  18. Amir Zadeh, Paul Pu Liang, Jonathan Vanbriesen, Soujanya Poria, Edmund Tong, Erik Cambria, Minghai Chen, Louis-Philippe Morency
    ACL 2018 (oral presentation)
    [paper] [supp] [arXiv] [slides] [code]
  19. Efficient Low-rank Multimodal Fusion with Modality-Specific Factors
  20. Zhun Liu, Ying Shen, Varun Lakshminarasimhan, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    ACL 2018 (oral presentation)
    [paper] [arXiv] [slides] [code]
  21. Proceedings of the First Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML)
  22. Amir Zadeh, Paul Pu Liang, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer
    ACL 2018
    [proceedings] [website] [introduction] [datasets] [results]
  23. Seq2Seq2Sentiment: Multimodal Sequence to Sequence Models for Sentiment Analysis
  24. Hai Pham, Thomas Manzini, Paul Pu Liang, Barnabás Póczos
    ACL 2018 Grand Challenge and Workshop on Human Multimodal Language
    [paper] [arXiv]
  25. Multi-attention Recurrent Network for Human Communication Comprehension
  26. Amir Zadeh, Paul Pu Liang, Soujanya Poria, Prateek Vij, Erik Cambria, Louis-Philippe Morency
    AAAI 2018 (oral presentation)
    [paper] [supp] [arXiv] [slides] [code]
  27. Memory Fusion Network for Multi-view Sequential Learning
  28. Amir Zadeh, Paul Pu Liang, Navonil Mazumder, Soujanya Poria, Erik Cambria, Louis-Philippe Morency
    AAAI 2018 (oral presentation)
    [paper] [supp] [arXiv] [slides] [code]
  29. Robust Modulation Classification Under Uncertain Noise Conditions Using Recurrent Neural Networks
  30. Shisheng Hu, Yiyang Pei, Paul Pu Liang, Ying-Chang Liang
    GLOBECOM 2018
    [paper]
  31. Label-Assisted Transmission for Short Packet Communications: A Machine Learning Approach
  32. Qianqian Zhang, Paul Pu Liang, Yu-Di Huang, Yiyang Pei, Ying-Chang Liang
    IEEE TVT 2018
    [paper]
  33. A Machine Learning Approach to MIMO Communications
  34. Yu-Di Huang, Paul Pu Liang, Qianqian Zhang, Ying-Chang Liang
    ICC 2018
    [paper]

2017

  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 (*equal contributions)
    ICMI 2017 (oral presentation, honorable mention award)
    [paper] [arXiv] [slides]

Other Projects

  1. On the Convergence, Generalization and Recovery Guarantees of Deep Neural Networks
  2. Paul Pu Liang, Edgar Chen
    10-702 Statistical Machine Learning Course Project, 2018
    [paper]
  3. Self-Supervised Dueling Networks for Deep Reinforcement Learning
  4. Paul Pu Liang*, Xiang Xu* (*equal contributions)
    10-703 Deep Reinforcement Learning Course Project, 2017
    [paper] [poster]
  5. Machine Learning to Predict Neuronal Firing in a Multi-Neuron System
  6. Paul Pu Liang, Stephen Tsou, Akshay Kulkarni
    18-690 Neuroscience Course Project, 2017
    [poster]
  7. High Throughput Phenotyping with 3D CNNs in Ladder Networks
  8. Hanqi Sun, Paul Pu Liang, Yue Niu
    10-701 Machine learning (PhD) Course Project, 2016
    [paper] [poster]

Honors

Teaching

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.