Hi! I am a second year M.S. in Computer Science Student at Texas A&M University, advised by Prof. Shu Kong, Prof. James Caverlee and Prof. Deva Ramanan. I have completed my undergraduate degree in Computer Science and Engineering from Vellore Institute of Technology, Chennai. My research interests currently lie at the intersection of Computer Vision and Natural Language Processing, particularly in Vision Language Models and their application in multi-modal chatbots and diffusion models. My aim is to investigate and address the biases and limitations of these models, to develop more robust and fairer VLMs.

๐Ÿ”ฅ News

  • 2024.02: ย ๐ŸŽ‰๐ŸŽ‰ Our paper, โ€œThe Neglected Tails of Vision-Language Modelsโ€ has been accepted at CVPR 2024!
  • 2023.12: ย ๐ŸŽ‰๐ŸŽ‰ I will be presenting our paper, โ€œPrompting Scientific Names for Zero-Shot Species Recognitionโ€ at EMNLP 2023.
  • 2022.02: ย ๐ŸŽ‰๐ŸŽ‰ I was awarded the Texas A&M Computer Science departmental scholarship.

๐Ÿ“ Publications

CVPR 2024
sym

The Neglected Tails of Vision-Language Models.

Shubham Parashar^^, Zhiqiu Lin^^, Tian Liu^*^, Xianjue Dong, Yanan Li, Deva Ramanan, James Caverlee, Shu Kong

Project Paper

  • Our study is the first to reveal bias in popular VLMs like CLIP due to long-tailed training data.
  • To mitigate the bias, we propose a novel prompting method and retrieval augmented strategy.
  • Both our methods achieve a new SOTA and our retrieval augmented method is 100x cheaper on compute resources compared to the previous retrieval augmented strategies.
EMNLP 2023
sym

Prompting Scientific Names for Zero-Shot Species Recognition

Shubham Parashar, Zhiqiu Lin, Yanan Li, Shu Kong

Paper

  • We propose an embarassingly simple prompting method that boosts the zero-shot accuracy of VLMs on 4 fine-grained species recognition benchmarks by 2-5x.

๐Ÿ“– Education

  • 2022.08 - (now), M.S. in Computer Science, Texas A&M University, College Station, Texas
  • *2015.07 - 2019.05, Undergraduate, Vellore Institute of Technology University, Chennai, India

๐Ÿ’ป Experience

  • 2023.05 - 2023.08, HPE, Houston, Tx.
  • 2019.07 - 2022.09, PayPal, Bangalore, India