Maitreya Patel

Ph.D. Student, School of Computing & AI, Arizona State University.


I am a first-year Ph.D. student at Arizona State University (ASU). I receieved my master’s in computer science with a thesis in December 2022 from ASU.

I work with Yezhou Yang and Chitta Baral and closely collaborate with Tejas Gokhale (Ph.D. candidate).

My goal as a Ph.D. student is to pursue research in the domain of Robust and Efficient Multi-modal representation learning. To achieve this, I genuinely believe that Counterfactual/Causal Reasoning will play the most important role. Apart from this, I’m super interested in using Language as a Computation tool for robotics tasks and Visual Language Navigation.

Apart from academics, I like to work on interesting open-source projects. Recently, I’m spending my free time developing reliability-checklist (v0.1.0 is out) and not-so-secure-ai (under review for product market fit).


Apr 5, 2023 :fire: Releasing reliability-checklist framework for holistic language model evaluations :fire:
Nov 4, 2022 Defended my master’s thesis; committee: Yezhou Yang (Chair), Chitta Baral (member), and Kookjin Lee (member)
Oct 6, 2022 Two long papers got accepted at EMNLP main conference. :sparkles: :smile:
Aug 2, 2022 I will be continuing my research as PhD student at ASU!
May 12, 2022 I will be working at LatentAI for the summer as AI/ML Intern.

selected publications

  1. CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering
    Maitreya PatelTejas GokhaleChitta Baral, and Yezhou Yang
    In EMNLP, Main Conference – 2022

  2. Benchmarking generalization via in-context instructions on 1,600+ language tasks
    Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, and  others
    In EMNLP, Main Conference – 2022

  3. MSpeC-Net: Multi-Domain Speech Conversion Network
    Harshit Malaviya, Jui Shah, Maitreya Patel, Jalansh Munshi, and Hemant A Patil
    In 45th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020

  4. CinC-GAN for Effective F0 prediction for Whisper-to-Normal Speech Conversion
    Maitreya Patel, Mirali Purohit, Jui Shah, and Hemant A Patil
    In 28th European Signal Processing Conference (EUSIPCO) 2020

  5. Weak Speech Supervision: A case study of Dysarthria Severity Classification
    Mirali Purohit, Mihir ParmarMaitreya Patel, Harshit Malaviya, and Hemant A Patil
    In 28th European Signal Processing Conference (EUSIPCO) 2020

  6. Novel adaptive generative adversarial network for voice conversion
    Maitreya PatelMihir Parmar, Savan Doshi, Nirmesh J Shah, and Hemant A Patil
    In 11th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) 2019

  7. Effectiveness of cross-domain architectures for whisper-to-normal speech conversion
    Mihir Parmar, Savan Doshi, Nirmesh J Shah, Maitreya Patel, and Hemant A Patil
    In 27th European Signal Processing Conference (EUSIPCO) 2019