4 papers · 1 filter
Grid-Supervised Flow Refinement for Wireless Localization
Taekyun Lee, Tommaso Balercia, Heasung Kim +2
This paper introduces FlowLoc, a framework for high-accuracy user equipment positioning from channel state information observed at multiple base stations. The input is a magnitude…
Residual Diffusion Models for Variable-Rate Joint Source Channel Coding of MIMO CSI
Sravan Kumar Ankireddy, Heasung Kim, Joonyoung Cho +1
Despite significant advancements in deep learning based CSI compression, some key limitations remain unaddressed. Current approaches predominantly treat CSI compression as a source…
Generative Diffusion Model-based Compression of MIMO CSI
Heasung Kim, Taekyun Lee, Hyeji Kim +6
While neural lossy compression techniques have markedly advanced the efficiency of Channel State Information (CSI) compression and reconstruction for feedback in MIMO communication…
Efficient Weighted Sampling via Score-based Generative Models
Heasung Kim, Taekyun Lee, Hyeji Kim +1
Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-rang…