PIDT: Physics-Informed Digital Twin for Optical Fiber Parameter Estimation
We propose a physics-informed digital twin for optical fiber parameter estimation, combining a parameterized split-step method with a physics-informed loss.
Hello! I am a second-year PhD student at the MLC Lab, part of the Communication Systems Group, Chalmers University of Technology, Sweden. I am supervised by Assoc. Prof. Christian Häger, Prof. Erik Agrell, and Prof. Magnus Karlsson.
Previously, I completed my Master's thesis at IVRL, EPFL, working with Prof. Sabine Süsstrunk, Yufan Ren, and Prof. Søren Forchhammer.
I hold a Master's degree from Technical University of Denmark (DTU) and a Bachelor's degree from Northeast Electric Power University.
I am passionate about utilizing advanced ML algorithms to solve problems in communication systems, specifically joint optical fiber sensing and communication (OISAC/OJSAC), and implementing algorithms via FPGA. I am also deeply interested in generative models for 3D/2D editing.
If you are interested in doing thesis projects or research collaborations, please feel free to contact me!
We propose a physics-informed digital twin for optical fiber parameter estimation, combining a parameterized split-step method with a physics-informed loss.
We leverage wavelets to decompose images into different spatial resolutions across multiple frequency bands, enabling precise modifications across different levels of detail.
Proposed a wavelet-based Score Distillation Sampling (SDS) method to generate high-quality textures for complex mesh objects.
Resolving multi-view inconsistency in 3D generation by leveraging geometry-conditioned diffusion models.
Investigated ML tools for pre/post-compensation of linear and nonlinear signal distortions in optical transmitters.