Related papers: Structured Masked Diffusion for Joint Multiuser De…

Under limited feedback, channel state information (CSI) reconstruction for multiuser multiple-input multiple-output (MU-MIMO) precoding is challenging, since the precoder should provide not only beamforming gain, but also robust suppression…

In this paper, we address the message-passing receiver design for the 3D massive MIMO-OFDM systems. With the aid of the central limit argument and Taylor-series approximation, a computationally efficient receiver that performs joint channel…

The use of channel output feedback to improve the reliability of fading channels has received scant attention in the literature. In most work on feedback for fading channels, only channel state information (CSI) feedback has been exploited…

Coherent diffractive imaging (CDI) provides new opportunities for high resolution X-ray imaging with simultaneous amplitude and phase contrast. Extensions to CDI broaden the scope of the technique for use in a wide variety of experimental…

Dense prediction tasks have enjoyed a growing complexity of encoder architectures, decoders, however, have remained largely the same. They rely on individual blocks decoding intermediate feature maps sequentially. We introduce banks, shared…

Multimodal fusion faces two robustness challenges: noisy inputs degrade representation quality, and missing modalities cause prediction failures. We propose DCER, a unified framework addressing both challenges through dual-stage compression…

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the…

Based on the concept of constructive interference (CI), multiuser interference (MUI) has recently been shown to be beneficial for communication secrecy. A few CI-based secure precoding algorithms have been proposed that use both the channel…

This paper investigates the linear precoder design that maximizes the average mutual information of multiple-input multiple-output channels with finite-alphabet inputs and statistical channel state information known at the transmitter. This…

Transformer-based NLP models are powerful but have high computational costs that limit deployment. Finetuned encoder-decoder models are popular in specialized domains and can outperform larger more generalized decoder-only models, such as…

We frame embedding inversion as conditional masked diffusion, recovering all tokens in parallel through iterative denoising rather than sequential autoregressive generation. A masked diffusion language model is conditioned on the target…

Recent work in multilingual translation advances translation quality surpassing bilingual baselines using deep transformer models with increased capacity. However, the extra latency and memory costs introduced by this approach may make it…

Cloud contamination severely degrades the usability of remote sensing imagery and poses a fundamental challenge for downstream Earth observation tasks. Recently, diffusion-based models have emerged as a dominant paradigm for remote sensing…

Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO…

In this work, we derive a lower bound on the training-based achievable downlink (DL) sum rate (SR) of a multi-user multiple-input-single-output (MISO) system operating in frequency-division-duplex (FDD) mode. Assuming linear minimum mean…

Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding for structured and symbolic generation. However, standard training…

Recently, we introduced a new class of finite alphabet iterative decoders (FAIDs) for low-density parity-check (LDPC) codes. These decoders are capable of surpassing belief propagation in the error floor region on the Binary Symmetric…

While neural lossy compression techniques have markedly advanced the efficiency of Channel State Information (CSI) compression and reconstruction for feedback in MIMO communications, efficient algorithms for more challenging and practical…

Information transmission over a multiple-input-multiple-output (MIMO) fading channel with imperfect channel state information (CSI) is investigated, under a new receiver architecture which combines the recently proposed generalized nearest…

Channel state information (CSI) feedback is a challenging issue in frequency division multiplexing (FDD) massive MIMO systems. This paper studies a cooperative feedback scheme, where the users first exchange their CSI with each other by…