Z
Zhun Liu
Researcher at Carnegie Mellon University
Publications - 10
Citations - 913
Zhun Liu is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Tensor & Nonverbal communication. The author has an hindex of 6, co-authored 8 publications receiving 252 citations.
Papers
More filters
Journal Article
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model
Shaden Smith,Md. Mostofa Ali Patwary,Brandon Norick,Patrick LeGresley,Samyam Rajbhandari,Jared Casper,Zhun Liu,Shrimai Prabhumoye,George Zerveas,Vijay Anand Korthikanti,Elton Zhang,Rewon Child,Reza Yazdani Aminabadi,Julie Bernauer,Xia Song,Mohammad Shoeybi,Yuxiong He,Mike Houston,Saurabh Tiwary,B. Catanzaro +19 more
TL;DR: The infrastructure as well as the 3D parallelism methodology used to train the largest monolithic transformer based language model, Megatron-Turing NLG 530B (MT-NLG), with 530 billion parameters is presented.
Journal ArticleDOI
Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors.
TL;DR: This article proposed the Recurrent Attended Variation Embedding Network (RAVEN) that models the fine-grained structure of nonverbal subword sequences and dynamically shifts word representations based on nonverbal cues.
Proceedings ArticleDOI
Efficient Low-rank Multimodal Fusion With Modality-Specific Factors
Zhun Liu,Ying Shen,Varun Bharadhwaj Lakshminarasimhan,Paul Pu Liang,Amir Zadeh,Louis-Philippe Morency +5 more
TL;DR: In this article, the authors proposed a low-rank tensor based multimodal fusion method for sentiment analysis, speaker trait analysis, and emotion recognition, which achieved competitive results on all these tasks while drastically reducing computational complexity.
Posted Content
Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
Paul Pu Liang,Zhun Liu,Yao-Hung Hubert Tsai,Qibin Zhao,Ruslan Salakhutdinov,Louis-Philippe Morency +5 more
TL;DR: A regularization method based on tensor rank minimization is presented based on the observation that high-dimensional multimodal time series data often exhibit correlations across time and modalities which leads to low-rank tensor representations.
Posted Content
Efficient Low-rank Multimodal Fusion with Modality-Specific Factors
Zhun Liu,Ying Shen,Varun Bharadhwaj Lakshminarasimhan,Paul Pu Liang,Amir Zadeh,Louis-Philippe Morency +5 more
TL;DR: The Low-rank Multimodal Fusion method is proposed, which performs multimodal fusion using low-rank tensors to improve efficiency and is indeed much more efficient in both training and inference compared to other methods that utilize tensor representations.