Salaheldin Y. Mohamed

pro.png

I am currently a Doctoral Researcher at Télécom Paris, Institut Polytechnique de Paris. Previously, I was a master’s thesis student at the Max Planck Institute for Informatics, supervised by Prof. Dr. Christian Theobalt. My work focuses on generative vision, controlled video, and image synthesis. I am particularly interested in developing physically plausible and realistic video and image models.

selected publications

  1. refree.png
    ReFree: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech Guidance
    Salaheldin Mohamed, M. Hamza Mughal, Rishabh Dabral, and 1 more author
    arXiv preprint arXiv:2606.13304, 2026
  2. pub4.png
    Shielddiff: Suppressing sexual content generation from diffusion models through reinforcement learning
    Dong Han✱, Salaheldin Mohamed✱, and Yong Li
    arXiv preprint arXiv:2410.05309, 2024
    ✱These authors contributed equally
  3. p1.png
    Fusion is all you need: Face Fusion for Customized Identity-Preserving Image Synthesis
    Salaheldin Mohamed, Dong Han, and Yong Li
    arXiv preprint arXiv:2409.19111, 2024
  4. pub3.png
    Diffusion-based Identity-Preserving Facial Privacy Protection
    Dong Han✱, Salaheldin Mohamed✱, Yong Li, and 1 more author
    In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
    ✱These authors contributed equally