معرفی
Fadli Damara is a PhD student in the Machine Learning Group at the Technical University of Berlin, advised by Prof. Dr. Klaus-Robert Müller and Dr. Shinichi Nakajima. He is also a Research Scientist at the Berlin Institute for the Foundations of Learning and Data (BIFOLD), focusing on probabilistic modeling and inference. His work integrates generative models, diffusion processes, and optimal transport theory with applications in inverse problems and signal processing.
Education:
- M.Sc. in Electrical Engineering, Technical University of Berlin (2023)
Research Interests: Damara’s research spans generative models (diffusion models), inverse problems, information theory, and signal separation. He explores acceleration techniques for diffusion models via Schrödinger bridges and consistency models, while applying these to radio spectrum analysis and neural source-channel coding. His work bridges theoretical foundations with practical applications in 6G telecommunications and data-driven signal processing.
Key Contributions:
- Developed Transformer U-Net and finetuned WaveNet models for RF signal separation (2nd place in ICASSP 2024 Challenge).
- Advanced fast reconstruction algorithms using conditional GANs and network-projected gradient descent (up to 175x speed-up).
Labs & Teams: Active in the Probabilistic Modeling and Inference Lab (BIFOLD) and previously collaborated with the Fraunhofer Heinrich-Hertz Institute on 6G research.
