Nihal Nayak


I am a Ph.D. candidate of Computer Science at Brown University. I work with Stephen Bach on learning with limited labeled data and zero-shot learning.

In summer 2022, I interned at ASAPP with Clemens Rosenbaum and Ethan R. Elenberg on estimating the quality of clusterings.

Before my Ph.D., I worked as a NLP Engineer at Stride.AI. I have also worked with Prof. H S Jamadagni at the Indian Institute of Science (IISc) as an Intern and then briefly as a Project Assistant.

CV (Updated in October, 2022)

Email : nnayak2 [at] cs [dot] brown [dot] edu


Oct 5, 2022 Excited to share new pre-print on evaluating clusterings with few labeled data points.
Jul 14, 2022 Our work ZSL-KG was accepted to TMLR.
Apr 10, 2022 New pre-print out: Learning to Compose Soft Prompts for Compositional Zero-Shot Learning!
Jan 19, 2022 T0 was accepted to ICLR 2022.

selected publications

  1. ArXiv
    CEREAL: Few-Sample Clustering Evaluation
    Nihal V. Nayak, Ethan R. Elenberg, and Clemens Rosenbaum
    ArXiv 2022
  2. TMLR
    Zero-Shot Learning with Common Sense Knowledge Graphs
    Nihal V. Nayak, and Stephen H. Bach
    Transactions on Machine Learning Research 2022
  3. ArXiv
    Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
    Nihal V. Nayak, Peilin Yu, and Stephen H. Bach
    ArXiv 2022
  4. ICLR
    Multitask Prompted Training Enables Zero-Shot Task Generalization
    Victor Sanh, Albert Webson, Colin Raffel,  Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, Manan Dey, M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani,  Nihal V. Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian Jiang, Han Wang, Matteo Manica, Sheng Shen, Zheng Xin Yong, Harshit Pandey, Rachel Bawden, Thomas Wang, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Andrea Santilli, Thibault Fevry, Jason Alan Fries, Ryan Teehan, Stella Biderman, Leo Gao, Tali Bers, Thomas Wolf, and Alexander M. Rush
    In International Conference on Learning Representations (ICLR) 2022