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

arXiv: https://arxiv.org/abs/2606.00263 · HTML: https://mlsanity.com/paper/2606.00263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 12 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 3 of 3)

- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Channelformer: Attention based Neural Solution for Wireless Channel Estimation and Effective Online Training](https://mlsanity.com/paper/2302.04368/) (2023)
- [Diffusion Inpainting MIMO-OFDM Channels with Limited Noisy Observations](https://mlsanity.com/paper/2604.09039/) (2026)

## 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.