# Soft Graph Diffusion Transformer for MIMO Detection

arXiv: https://arxiv.org/abs/2605.00449 · HTML: https://mlsanity.com/paper/2605.00449/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models.
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 1 May 2026.

## Placed in

- Diffusion models / [Diffusion for compression and wireless](https://mlsanity.com/diffusion/diffusion-for-compression-and-wireless/)

## Builds on (most cited first, 10 of 10)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Error Correction Code Transformer](https://mlsanity.com/paper/2203.14966/) (2022)
- [Deep MIMO Detection](https://mlsanity.com/paper/1706.01151/) (2017)
- [CrossMPT: Cross-attention Message-Passing Transformer for Error Correcting Codes](https://mlsanity.com/paper/2405.01033/) (2024)
- [RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection](https://mlsanity.com/paper/2007.00140/) (2020)
- [Memory AMP](https://mlsanity.com/paper/2012.10861/) (2020)
- [Message Passing Meets Graph Neural Networks: A New Paradigm for Massive MIMO Systems](https://mlsanity.com/paper/2302.06896/) (2023)
- [Prediction--Loss Alignment for Sampler--Robust Flow Matching Training](https://mlsanity.com/paper/2602.10420/) (2026)
- [Large Model Enabled Embodied Intelligence for 6G Integrated Perception, Communication, and Computation Network](https://mlsanity.com/paper/2512.15109/) (2025)

## Abstract (arXiv)

Learning-based MIMO detection has shown strong empirical performance, yet existing methods typically rely on fixed-depth architectures without explicitly modeling the progressive refinement of symbol estimates. In this paper, we revisit MIMO detection from a flow matching perspective and propose the Soft Graph Diffusion Transformer (SGDiT), which reformulates detection as a noise-level-conditioned denoising process that progressively transforms a Gaussian initialization toward the posterior conditioned on channel observations. An adaptive layer normalization (AdaLN)-conditioned soft graph transformer is employed to parameterize the denoising dynamics, enabling stage-aware information integration between observation and symbol domains. To better align with the discrete nature of symbol detection, we further adopt a cross-entropy-based training objective that directly models bit-wise posterior probabilities, providing a more suitable inductive bias than conventional regression-based formulations. Experimental results across various MIMO system configurations demonstrate that SGDiT achieves competitive bit error rate (BER) performance compared with representative baselines. Furthermore, the proposed model exhibits good generalization capability across different channel conditions. Overall, the SGDiT framework provides an effective and practical approach for neural MIMO detection.