Taneesh Gupta

Research Fellow, Microsoft Research

tanish.jpg

I am a Research Fellow at Microsoft Research India, working on LLM alignment, preference optimization, and efficient AI architectures. My work revolves around enhancing large language models (LLMs) through multi-preference optimization, reward modeling, and structured efficiency improvements. Prior to my current role, I completed my B.Tech in Computer Science and Engineering & Engineering Physics from IIT (ISM) Dhanbad. During my studies, I interned at Microsoft Research, CMU AirLab, Sprinklr, Sony Research India, and ShareChat, where I gained hands-on experience in inference optimization, multimodal learning, and AI-driven applications, contributing to research and engineering projects across these domains.

2025

  1. AMPO_illustration.jpg
    AMPO: Active Multi-Preference Optimization
    Taneesh Gupta, Rahul Madhavan, Xuchao Zhang, Chetan Bansal, and Saravan Rajmohan
    2025
    arXiv
  2. SWEPO_illustration.jpg
    SWEPO: Simultaneous Weighted Preference Optimization for Group Contrastive Alignment
    Taneesh Gupta, Rahul Madhavan, Xuchao Zhang, Chetan Bansal, and Saravan Rajmohan
    2025
    arXiv
  3. REFA: Reference Free Alignment for multi-preference optimization
    Taneesh Gupta, Rahul Madhavan, Xuchao Zhang, Chetan Bansal, and Saravan Rajmohan
    2025
    arXiv
  4. CARMO_illustration.jpg
    CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling
    Taneesh Gupta, Shivam Shandilya, Xuchao Zhang, Rahul Madhavan, Supriyo Ghosh, Chetan Bansal, and 2 more authors
    2025
    arXiv

2024

  1. mia_pull_fig.png
    Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets
    Cherie Ho, Jiaye Zou, Omar Alama, Sai Mitheran Jagadesh Kumar, Cheng-Yu Chiang, Taneesh Gupta, and 4 more authors
    In Advances in Neural Information Processing Systems, 2024
    HTML

2023

  1. On designing light-weight object trackers through network pruning: Use CNNs or transformers?
    Saksham Aggarwal, Taneesh Gupta, Pawan K Sahu, Arnav Chavan, Rishabh Tiwari, Dilip K Prasad, and 1 more author
    In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
    HTML