About

Nov. 2023-Present: AI Researcher at the Applied Machine Learning Lab, Jülich Supercomputing Centre. I study the effect of various perturbations on generative diffusion and flow-matching models, with early access to JUPITER, Europe’s first exascale supercomputer. I am completing my PhD at TU Dortmund University.

New

Exploring and Exploiting Stability in Latent Flow Matching
Rania Briq, Michael Kamp, Ohad Fried, Sarel Cohen, Stefan Kesselheim
Accepted at the International Conference on Machine Learning (ICML), 2026.
publications

Research interests

My research covered

• Stability in flow matching and diffusion models
• Generating human motion conditioned on multiple actions while interning at Amazon, followed up by scene-constrained generation.
• Generating human poses conditioned on text
• Optical and scene flow for human body tracking during my internship at Facebook Reality Labs.
• Human pose estimation and ordinal prediction for sets
• Weakly supervised semantic segmentation using object size constraints.

MSc in computer science, University of Bonn.

BSc in computer and software engineering, Technion.

Research internships

Applied scientist intern at Amazon Go, August 2021-August 2022. My work focused on synthesizing conditional human motion data.

Research intern at Facebook Reality Labs, August 2019-Jan. 2020. I worked on differentiable rendering and optical flow for human body tracking.

Teaching and supervision

Previously, alongside my doctoral studies, my responsibilities included teaching and supervising Master’s students, including Adversarial Synthesis of Human Pose from Text, which won the Best Master’s Thesis Award at the DAGM Young Researchers’ Forum 2020.