Varsha Kishore

prof_pic.png

PhD Candidate

Cornell University

I am a PhD candidate in the Computer Science Department at Cornell University, where I am advised by Kilian Q Weinberger. I work on applied machine learning broadly. Currently, I’m interested in developing end-to-end document retrieval methods and improving text diffusion models. In the past I’ve also worked on text evaluation metrics and steganography.

During my PhD, I’ve interned at Google with Ni Lao and John Blitzer, at Microsoft Research with Tristan Nauman and at ASAPP with David Sontag.

Before joining Cornell, I completed my undergraduate degree in Math and Computer Science at Harvey Mudd College. There, I conducted research in algorithms for computational biology with Prof. Yi-Chieh (Jessica) Wu.

Outside of research, I enjoy climbing, playing basketball and exploring the outdoors!

Publications and Preprints

  1. Latent Diffusion for Language Generation
    Justin Lovelace, Varsha Kishore, Chao Wan, Eliot Shaktman, and Kilian Q Weinberger
    In Advances in Neural Information Processing Systems (NeurIPS), 2023.
  2. IncDSI: Incrementally Updatable Document Retrieval
    Varsha Kishore, Chao Wan, Justin Lovelace, Yoav Artzi, and Kilian Q Weinberger
    In International Conference on Machine Learning (ICML), 2023.
  3. Correction with Backtracking Reduces Hallucination in Summarization
    Zhenzhen Liu, Chao Wan, Varsha Kishore, Jin Zhou, Minmin Chen, and 1 more author
    In arXiv preprint arXiv:2310.16176 , 2023.
  1. Learning Iterative Neural Optimizers for Image Steganography
    Varsha Kishore, Xiangyu Chen, and Kilian Q Weinberger
    In International Conference on Learning Representations (ICLR), 2022.
  2. Harnessing interpretable and unsupervised machine learning to address big data from modern X-ray diffraction
    Jordan Venderley, Krishnanand Mallayya, Michael Matty, Matthew Krogstad, Jacob Ruff, and 6 more authors
    Proceedings of the National Academy of Sciences , 2022.
  1. Fixed Neural Network Steganography: Train the images, not the network
    Varsha Kishore, Xiangyu Chen, Yan Wang, Boyi Li, and Kilian Q Weinberger
    In International Conference on Learning Representations (ICLR), 2021.
  1. Bertscore: Evaluating text generation with bert
    Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi
    In International Conference on Learning Representations (ICLR), 2019.

Teaching

Cornell University

Harvey Mudd College

  • Head TA for CS140: Algorithms
  • TA for CS42: Principles and Practice of Computer Science
  • TA for CS70: Data Structures and Program Development
  • TA for CS158: Machine Learning

Contact