Manish Kumar Govind

profile_pic.png

I am a first-year PhD student in Computer Science at the University of North Carolina, Charlotte under the guidance of Dr. Srijan Das. Prior to this, I received a master’s degree in Computer Science from UNC Charlotte and a bachelor’s degree in Computer Science from MNIT Jaipur. My research focuses on computer vision, robot learning, and multimodal AI, with a particular interest in developing generalist and foundational models for real-world robots.

News

Jun 2026 Two papers From My View to Yours and VisCoP are accepted to ECCV 2026
Feb 2025 One paper LLAVIDAL is accepted at CVPR 2025

Research

  1. World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays
    Manish Kumar Govind, Dominick Reilly, Smit Patel, Hieu Le, and 1 more author
    2026
    arXiv Code Website
  2. UniLACT-preview.png
    UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models
    Manish Kumar Govind, Dominick Reilly, Pu Wang, and Srijan Das
    2026
    arXiv Code Website
  3. VisCoP.png
    VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models
    Dominick Reilly, Manish Kumar Govind, Le Xue, and Srijan Das
    In ECCV, 2026
    arXiv
  4. foy_teaser.png
    From My View to Yours: Ego-to-Exo Transfer in VLMs for Understanding Activities of Daily Living
    Dominick Reilly, Manish Kumar Govind, Le Xue, and Srijan Das
    In ECCV, 2026
    arXiv
  5. llavidal.png
    LLAVIDAL: A Large Language Vision Model for Daily Activities of Living
    Dominick Reilly, Rajatsubhra Chakraborty, Arkaprava Sinha, Manish Kumar Govind, and 3 more authors
    In CVPR, 2025
    arXiv Code Website
  6. Fibottention.png
    Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads
    Ali Khaleghi Rahimian, Manish Kumar Govind, Subhajit Maity, Dominick Reilly, and 3 more authors
    In arXiv, 2024
    arXiv Code