I am an AI scientist (Ph.D. candidate of AI @ Carnegie Mellon University) and a computer engineer (B.S. University of Tehran). My research is focused on theoretical and empirical aspects of multimodal machine learning. I am also interested in fundamental unimodal research topics including facial and body analysis, audio source localization and separation, as well as language and dependency modeling. My ECE knowledge spans robotics, embedded systems, microprocessors, computer graphics,  game design, network administration, and software engineering. 

resume.jpg
images.png
kisspng-google-scholar-education-researc

News

  • Preprint: Pseudo-encoded Stochastic Variational Inference

  • Preprint: Variational Auto-Decoder: Neural generative modeling from partial data. 

  • Organizer: Multimodal Workshop @ CVPR 2020

  • Organizer: Grand-challenge and Workshop on Multimodal Language @ ACL 2020 (>1k in prize)

  • Organizer: Cross-Modal Learning in the Wild @ ICCV 2019

  • CVPR 2019: One paper accepted as oral presentation.

  • Invited Talk: Google San Francisco (2019).

  • Session Chair: AAAI 2019 Deep Learning session, and NLP session.

  • AAAI 2019: One paper accepted.

  • EMNLP 2018: One paper accepted as oral presentation.

  • ACL 2018: Two papers accepted as oral presentation.

  • AAAI 2018: Two papers accepted as oral presentation.

  • Organizer: Grand-challenge and Workshop on Multimodal Language @ ACL 2018

  • EMNLP 2017: One paper accepted as oral presentation.

  • ACL 2017: Two papers accepted (one oral).