Neeraj Gangwar

gangwar2 [at] illinois [dot] edu

I am a Ph.D. student in Electrical and Computer Engineering at the University of Illinois Urbana-Champaign. I am a part of the MLP Group and am advised by Prof. Nickvash Kani. I also work with Prof. Suma Bhat.

Prior to joining grad school, I spent seven years in the software industry. I was part of the engineering teams at Myntra and Commonfloor. I also worked with two friends on a couple of startup ideas - Shoplane (a hyperlocal shopping app for fashion) and AIANash (AI-driven analytics to understand user intent).

I completed my Bachelor’s and Master’s degrees in Electronics and Communication Engineering from the Indian Institute of Technology Roorkee in 2014. I worked with Prof. Debashis Ghosh and Prof. MV Kartikeyan. I was also a member of SDSLabs.

news

Jan 2026 Two papers accepted at AISTATS 2026!
May 2025 Another summer at Amazon Search in Palo Alto, CA.
May 2024 Summer at Amazon Search in Palo Alto, CA.
Sep 2023 Our work on semantic representations for mathematical expressions is published in TMLR (Paper).
Aug 2023 Our NL4Opt work is published in CICM 2023 (Paper).
Dec 2022 First prize in the generation track of NL4Opt at NeurIPS 2022 (Certificate, Conference Page).
Aug 2021 Started grad school at Illinois.
Aug 2021 Last day in Myntra. Amazing 4.5 years!
Jun 2021 Our project to scale inventory reads to 1000x was published on the Myntra Engineering Blog.

selected publications

  1. AISTATS
    GiVA: Gradient-Informed Bases for Vector-Based Adaptation
    Neeraj Gangwar, Rishabh Deshmukh, Michael Shavlovsky, Hancao Li, Vivek Mittal, Lexing Ying, and Nickvash Kani
    (To appear) International Conference on Artificial Intelligence and Statistics (2026)
    Spotlight (top 2.5%)
  2. AISTATS
    Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
    Neeraj Gangwar, Anshuka Rangi, Rishabh Deshmukh, Holakou Rahmanian, Yesh Dattatreya, and Nickvash Kani
    (To appear) International Conference on Artificial Intelligence and Statistics (2026)
    arXiv
  3. MATH-AI
    Intermediate Fine-Tuning Improves Mathematical Reasoning in Smaller Models
    Neeraj Gangwar, Suma Bhat, and Nickvash Kani
    Workshop on Mathematical Reasoning and AI (Math-AI) at NeurIPS (2024)
    Code OpenReview
  4. TMLR
    Semantic Representations of Mathematical Expressions in a Continuous Vector Space
    Neeraj Gangwar, and Nickvash Kani
    Transactions on Machine Learning Research (2023)
    arXiv Code OpenReview