Related papers: Towards Unified AI Models for MU-MIMO Communicatio…

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

The development of efficient machine learning models for molecular systems representation is becoming crucial in scientific research. We introduce TensorNet, an innovative O(3)-equivariant message-passing neural network architecture that…

Unified multimodal transformers, which handle both generation and understanding tasks within a shared parameter space, have received increasing attention in recent research. Although various unified transformers have been proposed, training…

U-Nets are a go-to, state-of-the-art neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however their design and architecture is understudied. In this paper,…

Recent foundational models for tabular data, such as TabPFN, excel at adapting to new tasks via in-context learning, but remain constrained to a fixed, pre-defined number of target dimensions-often necessitating costly ensembling…

We present a novel and low-complexity massive multiple-input multiple-output (MIMO) precoding strategy based on novel findings concerning the subspace separability of Rician fading channels. Considering a uniform rectangular array at the…

The Muon optimizer has demonstrated strong empirical performance in pre-training large language models by performing matrix-level gradient (or momentum) orthogonalization in each layer independently. In this work, we propose TEON, a…

Cross-View Geo-Localization (CVGL) involves determining the localization of drone images by retrieving the most similar GPS-tagged satellite images. However, the imaging gaps between platforms are often significant and the variations in…

Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture. However, it remains underexplored how to effectively coordinate these two capabilities for more effective and efficient reasoning.…

Unified multimodal models (UMMs) aim to jointly perform multimodal understanding and generation within a single framework. We present TUNA, a native UMM that builds a unified continuous visual representation by cascading a VAE encoder with…

We introduce a hybrid Quantum Neural Networks (QNN) architecture for the efficient user scheduling in 5G/Beyond 5G (B5G) massive Multiple Input Multiple Output (MIMO) systems, addressing the scalability issues of traditional methods. By…

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model…

End-to-end autoencoder (AE) learning has the potential of exceeding the performance of human-engineered transceivers and encoding schemes, without a priori knowledge of communication-theoretic principles. In this work, we aim to understand…

Unified multimodal models have recently shown remarkable gains in both capability and versatility, yet most leading systems are still trained from scratch and require substantial computational resources. In this paper, we show that…

In traditional multiple-input multiple-output (MIMO) communication systems, the antenna spacing is often no smaller than half a wavelength. However, by exploiting the coupling between more closely-spaced antennas, a superdirective array may…

Equivariant neural networks have been widely used in a variety of applications due to their ability to generalize well in tasks where the underlying data symmetries are known. Despite their successes, such networks can be difficult to…

With the powerful reasoning capabilities of large language models (LLMs) and vision-language models (VLMs), many recent works have explored using them for decision-making. However, most of these approaches rely solely on language-based…

We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the…

In this paper, we propose network massive multiple- input multiple-output (MIMO) systems, where three radio units (RUs) connected via one digital unit (DU) support multiple user equipments (UEs) at a cell-boundary through the same radio…

In recent years and with introduction of 5G cellular network and communication, researchers have shown great interest in Multiple Input Multiple Output (MIMO) communication, an advanced technology. Many studies have examined the problem of…