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 am working alongside Yezhou Yang and Chitta Baral. I closely collaborate with Tejas Gokhale and Changhoon Kim.

My focus lies in the domain of Robust and Reliability for Vision-Language. Currently, I specialize in computer vision, specifically generative and diffusion models, concept algebra, model attribution, and few-shot learning. I firmly believe that advancing Counterfactual/Causal Reasoning is essential for enhancing the reliability of machine learning systems in the long run.

Aside from academics, I enjoy working on intriguing open-source projects. Recently, I have dedicated my free time to developing reliability-checklist (v0.1.0 released) and AInos (under review for product market fit).


Sep 9, 2023 Looking for students to help us with improving composition understanding of T2I models: Collection-of-Stable-Diffusion-Test-time-Plugins 🤝 🤝
Jun 8, 2023 :fire: Two new arXiv pre-prints on my recent works are released. :fire:
Apr 5, 2023 Releasing reliability-checklist framework for holistic language model evaluations
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:

Selected Publications

  1. ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
    Maitreya Patel Tejas GokhaleChitta Baral, and Yezhou Yang
    In arXiv (pre-print) – 2023

  2. WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
    Changhoon Kim*Kyle Min* Maitreya Patel , Sheng Cheng, and Yezhou Yang
    In arXiv (pre-print) – 2023

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

  4. 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

  5. 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

  6. 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

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

  8. Novel adaptive generative adversarial network for voice conversion
    Maitreya Patel Mihir 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

  9. 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