Salaheldin Y. Mohamed
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
-
ReFree: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech GuidancearXiv preprint arXiv:2606.13304, 2026 -
Shielddiff: Suppressing sexual content generation from diffusion models through reinforcement learningarXiv preprint arXiv:2410.05309, 2024✱These authors contributed equally -
Fusion is all you need: Face Fusion for Customized Identity-Preserving Image SynthesisarXiv preprint arXiv:2409.19111, 2024 -
Diffusion-based Identity-Preserving Facial Privacy ProtectionIn ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025✱These authors contributed equally