Skip to content
View benediktfesl's full-sized avatar

Block or report benediktfesl

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
benediktfesl/README.md

Dr. Benedikt Fesl

AI Research Engineer interested in signal processing, scientific machine learning, and domain-aware AI.

I like interpretable AI/ML methods that connect generative modeling, real-world signals, physical systems, and theory.

🧰 Published Software

  • diffusers-dmse — MSE-optimal diffusion model scheduler (DMSE) for the HuggingFace diffusers library.
  • cplx-gmm — Complex-valued Gaussian mixture models (GMMs) with a scikit-learn-style API.
  • gmm-estimator — GMM-based estimator for complex-valued linear inverse problems.
  • cplx-mfa — Complex-valued mixture of factor analyzers (MFAs) with a scikit-learn-style API.
  • mfa-estimator — MFA-based estimator for complex-valued linear inverse problems.
  • nrCSIIMConfig — Explicit CSI-IM resource configuration for 5G NR in MATLAB.

📚 Selected Publications

  • B. Fesl, “Generative Model-Aided Channel Estimation Design and Optimality Analysis,” Ph.D. dissertation, Technical University of Munich, 2025. [Link]

  • B. Fesl, B. Böck, F. Strasser, M. Baur, M. Joham and W. Utschick, “On the Asymptotic Mean Square Error Optimality of Diffusion Models,” 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025. [Link]

  • B. Fesl, M. Baur, F. Strasser, M. Joham and W. Utschick, “Diffusion-Based Generative Prior for Low-Complexity MIMO Channel Estimation,” IEEE Wireless Communications Letters, vol. 13, no. 12, pp. 3493–3497, 2024. [Link]

  • B. Fesl, N. Turan, B. Böck, and W. Utschick, “Channel Estimation for Quantized Systems Based on Conditionally Gaussian Latent Models,” IEEE Transactions on Signal Processing, vol. 72, pp. 1475–1490, 2024. [Link]

  • M. Baur, B. Fesl and W. Utschick, “Leveraging Variational Autoencoders for Parameterized MMSE Estimation,” IEEE Transactions on Signal Processing, vol. 72, pp. 3731–3744, 2024. [Link]

  • B. Fesl, M. Koller and W. Utschick, “On the Mean Square Error Optimal Estimator in One-Bit Quantized Systems,” IEEE Transactions on Signal Processing, vol. 71, pp. 1968–1980, 2023. [Link]

Full list: Google Scholar

🔎 Interests

Domain-aware AI/ML · Signal Processing · Wireless Systems · Inverse Problems · Generative Models · Physics-Informed AI · Diffusion Models

📬 Contact

Feel free to reach out via LinkedIn.

Pinned Loading

  1. Diffusion_channel_est Diffusion_channel_est Public

    Source code of the Paper "Diffusion-Based Generative Prior for Low-Complexity MIMO Channel Estimation"

    Python 77 12

  2. diffusers-dmse diffusers-dmse Public

    PyPI package for MSE-optimal denoising with diffusion models.

    Python 1

  3. Quantized_Channel_Estimation Quantized_Channel_Estimation Public

    Implementation of the Paper "Channel Estimation for Quantized Systems based on Conditionally Gaussian Latent Models".

    Python 14 3

  4. cplx-gmm cplx-gmm Public

    PyPI package for complex-valued Gaussian mixture models with a scikit-learn-style API.

    Python 9 2

  5. Diffusion_MSE Diffusion_MSE Public

    Implementation of the paper "On the Asymptotic Mean Square Error Optimality of Diffusion Models."

    Python 15 1

  6. cplx-mfa cplx-mfa Public

    PyPI package for complex-valued mixture of factor analyzers with a scikit-learn-style API.

    Python 2