MPI-INF Logo
Homepage

Contact

Firstname Lastname

Muhammad Hamza Mughal

Max-Planck-Institut für Informatik
D6: Visual Computing and Artificial Intelligence
 office: Campus E1 4, Room 117
Saarland Informatics Campus
66123 Saarbrücken
Germany
 Personal Homepage: m-hamza-mughal.github.io
 email: Get my email address via email
 phone: +49 681 9325 4556

Research Profile

I am a Ph.D. student at the Max Planck Institute for Informatics advised by Prof. Christian Theobalt and Prof. Vera Demberg. I am also a member of the RTG 2853 "Neuroexplicit Models of Language, Vision, and Action".

My work involves exploring relations between speech, language and gestures/motion in human interactions, grounding human motion with language and enabling virtual humans to interact by means of multimodal learning.

Research Interests

  • Vision/Animation: Human Gesture Synthesis and Analysis, Multi-modal Motion Synthesis, Generative Modeling
  • Language:Relations b/w linguistic structures and gestures, Discourse and communication

Publications

    Enhancing Spoken Discourse Modeling in Language Models Using Gestural Cues.
    Varsha Suresh, M. Hamza Mughal, Christian Theobalt, Vera Demberg.
    ACL 2025 Oral (8% of accepted papers)
    [paper]

    Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis.
    M. Hamza Mughal, Rishabh Dabral, Merel C.J. Scholman, Vera Demberg, Christian Theobalt.
    CVPR 2025
    [paper] [project page]

    ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis.
    Muhammad Hamza Mughal, Rishabh Dabral, Ikhsanul Habibie, Lucia Donatelli, Marc Habermann and Christian Theobalt.
    CVPR 2024
    [paper] [project page]

    MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis.
    Rishabh Dabral, Muhammad Hamza Mughal, Vladislav Golyanik and Christian Theobalt.
    CVPR 2025 Highlight (10% of accepted papers)
    [paper] [project page]

Education