Paul 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 @pliang279 @lpwinniethepu

I am a third-year Ph.D. student in the Machine Learning Department at Carnegie Mellon University, advised by Louis-Philippe Morency and Ruslan Salakhutdinov. My long-term research goal is to build socially intelligent embodied agents with the ability to perceive and engage in multimodal human communication. As steps towards this goal, my research focuses on 1) the fundamentals of multimodal learning, specifically the representation, translation, fusion, and alignment of heterogeneous data sources, 2) human-centered language, vision, speech, robotics, and healthcare applications, as well as 3) the real-world deployment of socially intelligent agents by improving fairness, robustness, and interpretability in real-world applications. My research has been recognized by paper awards at the NeurIPS 2019 workshop on federated learning and ICMI 2017. I regularly organize the workshop on multimodal learning (NAACL 2021, ACL 2020, and ACL 2018) and have also participated as an organizer for the workshop on tensor networks at NeurIPS 2020 and a workflow chair for ICML 2019.

Previously, I received an M.S. in Machine Learning and a B.S. with University Honors in Computer Science from CMU, where I am grateful for the mentorship of Louis-Philippe Morency, Ruslan Salakhutdinov, Tai Sing Lee, Ryan Tibshirani, and Roni Rosenfeld. I have also been fortunate to spend time at Facebook AI Research, Nvidia AI, Google Research, and RIKEN Artificial Intelligence Project.

[News] [Education] [Experience] [Publications] [Honors] [Teaching] [Students] [Talks] [Activities]





(* denotes joint first-authors)


  1. Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies
  2. Paul Pu Liang, Manzil Zaheer, Yuan Wang, Amr Ahmed
    ICLR 2021
  3. An Investigation of how Label Smoothing Affects Generalization
  4. Blair Chen, Liu Ziyin, Zihao Wang, Paul Pu Liang


  1. Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment
  2. Paul Pu Liang, Peter Wu, Liu Ziyin, Louis-Philippe Morency, Ruslan Salakhutdinov
    NeurIPS 2020 Workshop on Meta Learning
    [arxiv] [code]
  3. Multimodal Privacy-preserving Mood Prediction from Mobile Data: A Preliminary Study
  4. Terrance Liu*, Paul Pu Liang*, Michal Muszynski, Ryo Ishii, David Brent, Randy Auerbach, Nicholas Allen, Louis-Philippe Morency
    NeurIPS 2020 Workshop on Machine Learning for Mobile Health
  5. MOSEAS: A Multimodal Language Dataset for Spanish, Portuguese, German and French
  6. Amir Zadeh, Yansheng Cao, Simon Hessner, Paul Pu Liang, Soujanya Poria, Louis-Philippe Morency
    EMNLP 2020
  7. Diverse and Admissible Trajectory Prediction through Multimodal Context Understanding
  8. Seong Hyeon Park, Gyubok Lee, Manoj Bhat, Jimin Seo, Minseok Kang, Jonathan Francis, Ashwin R. Jadhav, Paul Pu Liang, Louis-Philippe Morency
    ECCV 2020
    CVPR 2020 Argoverse competition (honorable mention award)
    [arXiv] [code]
  9. Towards Debiasing Sentence Representations
  10. Paul Pu Liang, Irene Li, Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, Louis-Philippe Morency
    ACL 2020
    [arXiv] [code]
  11. On Emergent Communication in Competitive Multi-Agent Teams
  12. Paul Pu Liang, Jeffrey Chen, Ruslan Salakhutdinov, Louis-Philippe Morency, Satwik Kottur
    AAMAS 2020 (oral)
    NeurIPS 2019 Workshop on Emergent Communication
    [arXiv] [code] [slides]
  13. Empirical and Theoretical Studies of Multimodal Co-learning
  14. Amir Zadeh, Paul Pu Liang, Louis-Philippe Morency
    Elsevier Information Fusion 2020


  1. Think Locally, Act Globally: Federated Learning with Local and Global Representations
  2. Paul Pu Liang*, Terrance Liu*, Liu Ziyin, Nicholas Allen, Randy Auerbach, David Brent, Ruslan Salakhutdinov, Louis-Philippe Morency
    NeurIPS 2019 Workshop on Federated Learning (oral, distinguished student paper award)
    [arXiv] [code]
  3. Deep Gamblers: Learning to Abstain with Portfolio Theory
  4. Liu Ziyin, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda
    NeurIPS 2019
    [arXiv] [code] [poster]
  5. Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
  6. Paul Pu Liang*, Zhun Liu*, Yao-Hung Hubert Tsai, Qibin Zhao, Ruslan Salakhutdinov, Louis-Philippe Morency
    ACL 2019
    [arXiv] [poster]
  7. Multimodal Transformer for Unaligned Multimodal Language Sequences
  8. Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov
    ACL 2019
    [arXiv] [code]
  9. Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence
  10. Amir Zadeh, Michael Chan, Paul Pu Liang, Edmund Tong, Louis-Philippe Morency
    CVPR 2019 (oral)
    [paper] [code] [poster]
  11. Strong and Simple Baselines for Multimodal Utterance Embeddings
  12. Paul Pu Liang*, Yao Chong Lim*, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Louis-Philippe Morency
    NAACL 2019 (oral)
    [arXiv] [code] [slides]
  13. Learning Factorized Multimodal Representations
  14. Yao-Hung Hubert Tsai*, Paul Pu Liang*, Amir Zadeh, Louis-Philippe Morency, Ruslan Salakhutdinov
    ICLR 2019
    NeurIPS 2018 Workshop on Bayesian Deep Learning
    [arXiv] [code] [poster]
  15. Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities
  16. Hai Pham*, Paul Pu Liang*, Thomas Manzini, Louis-Philippe Morency, Barnabás Póczos
    AAAI 2019
    NeurIPS 2018 Workshop on Interpretability and Robustness in Audio, Speech and Language (oral)
    [arXiv] [code] [slides] [poster]
  17. Words can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors
  18. Yansen Wang, Ying Shen, Zhun Liu, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    AAAI 2019
    [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 (first runner-up award)
    [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)
    [arXiv] [slides] [poster]
  5. Multimodal Local-Global Ranking Fusion for Emotion Recognition
  6. Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency
    ICMI 2018
    [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
    [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)
    [arXiv] [code] [slides]
  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)
    [arXiv] [code] [slides]
  13. Multi-attention Recurrent Network for Human Communication Comprehension
  14. Amir Zadeh, Paul Pu Liang, Soujanya Poria, Prateek Vij, Erik Cambria, Louis-Philippe Morency
    AAAI 2018 (oral)
    [arXiv] [code] [slides]
  15. Memory Fusion Network for Multi-view Sequential Learning
  16. Amir Zadeh, Paul Pu Liang, Navonil Mazumder, Soujanya Poria, Erik Cambria, Louis-Philippe Morency
    AAAI 2018 (oral)
    [arXiv] [code] [slides]


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

Organized Workshop Proceedings

  1. Proceedings of the Second Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML)
  2. ACL 2020 Workshop Proceedings
    [proceedings] [website]
  3. Proceedings of the First Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML)
  4. ACL 2018 Workshop Proceedings
    [proceedings] [website] [introduction] [datasets] [results]



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.