avatar

M. Hamza Mughal

Ph.D. Student
Max-Planck Institute for Informatics
mmughal (at) mpi-inf.mpg.de


About Me

I am a Ph.D. student at the Max Planck Institute for Informatics advised by Prof. Christian Theobalt and Prof. Vera Demberg, and co-advised by Dr. Rishabh Dabral. I am also a member of the RTG 2853 “Neuroexplicit Models of Language, Vision, and Action”. Previously, I completed Master’s in Visual Computing from Saarland University and worked as a Research Assistant at the MPII.

My work focuses on Social Behavior Modelling for Digital Humans. More specifically, it involves research on behavior in humans across multi-modal signals (gestures, motion, speech and language), in order to enhance digital humans and their interactions.

Research Interests

Publications

  1. MIBURI: Towards Expressive Interactive Gesture Synthesis
    M. Hamza Mughal, Rishabh Dabral, Vera Demberg, Christian Theobalt
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, Denver.
    Best Demo Award
    Best Paper Award @ Interactive Physical AI Workshop-CVPR 2026
    PDF Code Project Page

  2. Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark
    Rajmund Nagy, Hendric Voss, Thanh Hoang-Minh, ..., M. Hamza Mughal, Rishabh Dabral, ..., Youngwoo Yoon, Gustav Eje Henter
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - Findings, 2026, Denver.
    PDF Project Page

  3. Modeling Turn-Taking with Semantically Informed Gestures
    Varsha Suresh*, M. Hamza Mughal*, Christian Theobalt, Vera Demberg (*:equal contribution)
    The 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL)-Findings, 2026, Rabat.
    PDF

  4. Enhancing Spoken Discourse Modeling in Language Models Using Gestural Cues
    Varsha Suresh, M. Hamza Mughal, Christian Theobalt, Vera Demberg
    The 63rd Annual Conference of the Association for Computational Linguistics (ACL), 2025, Vienna.
    Oral (Top 8% of selected papers)
    PDF

  5. Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
    M. Hamza Mughal, Rishabh Dabral, Merel C.J. Scholman, Vera Demberg, Christian Theobalt
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, Nashville.
    PDF Code Project Page

  6. ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis
    Muhammad Hamza Mughal, Rishabh Dabral, Ikhsanul Habibie, Lucia Donnatelli, Marc Habermann, Christian Theobalt
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Seattle.
    PDF Code Project Page Dataset

  7. MoFusion A Framework for Denoising-Diffusion-based Motion Synthesis
    Rishabh Dabral, Muhammad Hamza Mughal, Vladislav Golyanik, Christian Theobalt
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Vancouver.
    Highlight (Top 10% of selected papers)
    PDF Project Page

  8. Assisting UAV Localization Via Deep Contextual Image Matching
    Muhammad Hamza Mughal, Muhammad Jawad Khokar, Muhammad Shahzad
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2021.
    PDF Code Dataset

Timeline

2024 - Present  PhD student  MPII, Germany
2022 - 2023  Research Assistant  MPII, Germany
2021 - 2023  Master in Visual Computing  Saarland University, Germany
2021  Visiting Research Student (DAAD Scholar)  TUM, Germany
2020 - 2021  Machine Learning Lead  Scribe Audio, Pakistan
2019 - 2020  Computer Vision Engineer  VisionX, Pakistan
2015 - 2019  Bachelor in Electrical Engineering  NUST-SEECS, Pakistan

Academic Services


Powered by Jekyll and Minimal Light theme.