Martin Q. Ma

Martin Q. Ma 

Martin Q. Ma
Ph.D. student, Language Technology Institute,
School of Computer Science, Carnegie Mellon University
Email: martin.q.ma0 [at] gmail (dot) com

Google Scholar
DBLP
GitHub
Twitter

Research Summary

My primary interest is deep representation learning especially self-supervised learning and multimodal learning.

About Me

I am currently a Ph.D. student in School of Computer Science at Carnegie Mellon University, where I am very fortunate to have Louis-Philippe Morency as my supervisor. I am also very grateful to have been collaborating with Yao-Hung Hubert Tsai, Ruslan Salakhutdinov and Kun Zhang. Previously, I studied at Brandeis University where I was supervised by Pengyu Hong who generously introduced me to the world of research.

Highlights

Papers, codes, slides, blogs, and talk videos are available here.
- ICLR 2021, NeurIPS 2020 SSL Workshop: Relative Predictive Coding, a stabler, higher performing loss objective for better self-supervised contrastive learning.
- EMNLP 2020: Multimodal Routing, a method for interprete multimodal language analysis for sentiment analysis and emotion recognition.
- ICASSP 2020, (Oral) NeurIPS 2019 SEDL Workshop: Complex Transformer, a strong performing network for complex-valued time-series analysis.