mlsanityData to 7 Oct 2026

ReFLEX: Length-Generalizable CSI Denoising for MIMO-OFDM via Relative-Frequency Bias

arXiv 2606.00263 ↗First posted 29 May 2026eess.SP cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This letter studies CSI denoising for MIMO--OFDM with variable NR resource block (RB) allocations. ReFLEX is a length-generalizable Transformer whose frequency attention uses a relative-frequency position bias (RFPB) generated from subcarrier offsets. A single checkpoint handles unseen RB lengths and can be applied to sparse DM-RS observations in the tested RB5/RB10 PUSCH setup without retraining. In a 3GPP~TR~38.901 UMa NLOS channel, ReFLEX achieves about -9.6~dB NMSE on unseen RB lengths. In NR PUSCH/UL-SCH simulations, ReFLEX denoising followed by time-frequency interpolation reduces the 10% BLER threshold by about 2--3~dB.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 3 of its 12 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

3 of 12 references.

References · 3

  1. 2018Self-Attention with Relative Position Representationscited by 1,112
  2. 2023Channelformer: Attention based Neural Solution for Wireless Channel Estimation and Effective Online Trainingcited by 14
  3. 2026Diffusion Inpainting MIMO-OFDM Channels with Limited Noisy Observationscited by 1

Built on by

Not cited yet.