Gaurav Sahu

Pushing the frontiers of AI to accelerate science.

prof_pic.jpg

Mila - Quebec AI Institute

Montreal

QC, Canada

I am a postdoctoral fellow at Mila - Quebec AI Institute where I am priviledged to work with Prof. Chris Pal, and Prof. Laurent Charlin. Prior to that, I was a Ph.D. student at the NLP Lab of the University of Waterloo, advised by Prof. Olga Vechtomova working on developing mechanisms to extract the most out of LLMs for any NLP task, objective or subjective.

I earned a thesis-based M.Math. degree in Computer Science from the University of Waterloo. Prior to that, I got my B.Tech. degree in Manufacturing Science and Engineering from the Indian Institute of Technology Kharagpur (IIT Kharagpur), where I worked with Prof. Pawan Goyal on Program Synthesis for Natural Language.

Apart from research, I am much enthused by language and art. I love to sometimes engross myself with sketching and painting. Check out my art collection if you’d like! I have also been learning to play the piano, as well as to speak Japanese and French.

news

Jun 28, 2025 We won the best paper award for our work on computational creativity at ICCC 2025!
Apr 01, 2025 LitLLM gets accepted to TMLR 2025!
Jan 22, 2025 InsightBench gets accepted to ICLR 2025!
Jan 11, 2025 Starting my postdoc at Mila with Prof. Chris Pal and Prof. Laurent Charlin.
Dec 06, 2024 Successfully defended my Ph.D Defence!

selected publications

  1. Promptmix: A class boundary augmentation method for large language model distillation
    Gaurav Sahu, Olga Vechtomova, Dzmitry Bahdanau, and 1 more author
    arXiv preprint arXiv:2310.14192, 2023
  2. Insightbench: Evaluating business analytics agents through multi-step insight generation
    Gaurav Sahu, Abhay Puri, Juan Rodriguez, and 8 more authors
    arXiv preprint arXiv:2407.06423, 2024
  3. LitLLMs, LLMs for Literature Review: Are we there yet?
    Shubham Agarwal*, Gaurav Sahu*, Abhay Puri*, and 5 more authors
    arXiv preprint arXiv:2412.15249, 2024
  4. Computational Modeling of Artistic Inspiration: A Framework for Predicting Aesthetic Preferences in Lyrical Lines Using Linguistic and Stylistic Features
    Gaurav Sahu and Olga Vechtomova
    arXiv preprint arXiv:2410.02881, 2024