Related papers: Cascaded Transformer for Robust and Scalable SLA D…

With the emergence of new application areas such as cyber-physical systems and human-in-the-loop applications ensuring a specific level of end-to-end network latency with high reliability (e.g., 99.9%) is becoming increasingly critical. To…

Decoding in a Transformer based language model is inherently sequential as a token's embedding needs to pass through all the layers in the network before the generation of the next token can begin. In this work, we propose a new…

The growing complexity of neural networks hinders the deployment of distributed machine learning on resource-constrained devices. Split learning (SL) offers a promising solution by partitioning the large model and offloading the primary…

As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapted to real images without requiring their annotations. This…

Transformer has emerged as a powerful deep-learning technique for two-dimensional (2D) seismic data interpolation, owing to its global modeling ability. However, its core operation introduces heavy computational burden due to the quadratic…

We develop an unsupervised deep learning framework for real-time scalable and generalizable downlink beamforming in multi-user multiple-input single-output (MU-MISO) systems. The proposed semi-amortized lifted learning-to-optimize (SALLO)…

To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality…

This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a promising alternative to…

Reconfigurable Intelligent Surface (RIS) panels are envisioned as a key technology for sixth-generation (6G) wireless networks, providing a cost-effective means to enhance coverage and spectral efficiency. A critical challenge is the…

Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due to the quadratic…

Simultaneous recordings from thousands of neurons across multiple brain areas reveal rich mixtures of activity that are shared between regions and dynamics that are unique to each region. Existing alignment or multi-view methods neglect…

Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance. However, residual connections may make the model…

Interactive intelligent computing applications are increasingly prevalent, creating a need for AI/ML platforms optimized to reduce per-event latency while maintaining high throughput and efficient resource management. Yet many intelligent…

This paper develops a multi-port S-parameter framework for the analysis and optimization of stacked intelligent metasurfaces (SIMs) with unilateral active interconnections. By modeling each unit cell as a non-reciprocal two-port network,…

Unsupervised learning aims at the discovery of hidden structure that drives the observations in the real world. It is essential for success in modern machine learning. Latent variable models are versatile in unsupervised learning and have…

Channel state information (CSI) at transmitter is crucial for massive MIMO downlink systems to achieve high spectrum and energy efficiency. Existing works have provided deep learning architectures for CSI feedback and recovery at the…

Vision transformer family has dominated the satellite pan-sharpening field driven by the global-wise spatial information modeling mechanism from the core self-attention ingredient. The standard modeling rules within these promising…

The expanding scale of neural networks poses a major challenge for distributed machine learning, particularly under limited communication resources. While split learning (SL) alleviates client computational burden by distributing model…

We develop a novel graph-based trainable framework to maximize the weighted sum energy efficiency (WSEE) for power allocation in wireless communication networks. To address the non-convex nature of the problem, the proposed method consists…

Network slicing is a critical driver for guaranteeing the diverse service level agreements (SLA) in 5G and future networks. Inter-slice radio resource allocation (IS-RRA) in the radio access network (RAN) is very important. However, user…