Maharshi Gor

NLP Researcher | Engineer

Iribe 4108

8125 Paint Branch Dr

College Park, MD 20742


I am a first year Computer Science PhD student at the University of Maryland, College Park, currently working with Jordan Boyd-Graber. I am broadly interested in Natural Language Understanding and Representation; particularly in Question Answering (QA), Semantic structure understanding, Model Robustness and Interpretability.

Prior to UMD, I spent two years working at Google Research where I collaborated with several Language Research teams, with focus on Model Interpretation and Analysis for Question Answering, and Semi-Structured Text Understanding for QA and NLI.

In the past, I have also worked on some of the Computer vision and Machine Learning problems like: Human motion sequence modeling, Generative and Representation Learning and Adversarial Machine Learning.

I am quite excited about learning and applying Visually grounded contexts for Language Understanding tasks as well.


Jun 24, 2022 Our work “Toward Efficient Robust Training against Union of Lp Threat Models” is accepted as oral presentation at ADVML FRONTIERS @ ICML 2022.
May 23, 2022 I am spending my summer at X, the moonshot factory (formerly Google X) as PhD Research Resident, and will be working on Program Synthesis.
Apr 15, 2022 I am reviewing at NeurIPS 2022
Nov 22, 2021 I will be serving as a Program Committee member for SUKI: Workshop on Structured and Unstructured Knowledge Integration and DADC: Workshop on Dynamic Adversarial Data Collection at NAACL 2022
Sep 22, 2021 Our work “MATE: Multi-view Attention for Table Transformer Efficiency” selected for an oral presentation at EMNLP 2021.

Selected Publications

  1. EMNLP 2021
    MATE: Multi-view Attention for Table Transformer Efficiency
    In Empirical Methods in Natural Language Processing 2021
  2. EMNLP 2021
    Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracy
    Maharshi Gor, Kellie Webster, and Jordan Boyd-Graber
    In Empirical Methods in Natural Language Processing 2021
  3. ICCV 2019
    GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions
    Jogendra Nath Kundu, Maharshi Gor, Dakshit Agrawal, and R. Venkatesh Babu
    In Proceedings of the IEEE/CVF International Conference on Computer Vision 2019