Related papers: SEA: State-Exchange Attention for High-Fidelity Ph…
We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to…
Elastic actuation taps into elastic elements' energy storage for dynamic motions beyond rigid actuation. While Series Elastic Actuators (SEA) and Variable Stiffness Actuators (VSA) are highly sophisticated, they do not fully provide control…
Generative models of observations under interventions have been a vibrant topic of interest across machine learning and the sciences in recent years. For example, in drug discovery, there is a need to model the effects of diverse…
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…
Transformer-based models have achieved remarkable results in low-level vision tasks including image super-resolution (SR). However, early Transformer-based approaches that rely on self-attention within non-overlapping windows encounter…
Federated edge learning (FEEL) is a widely adopted framework for training an artificial intelligence (AI) model distributively at edge devices to leverage their data while preserving their data privacy. The execution of a power-hungry…
Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention…
Recently, end-to-end (E2E) models become a competitive alternative to the conventional hybrid automatic speech recognition (ASR) systems. However, they still suffer from speaker mismatch in training and testing condition. In this paper, we…
Transformers have demonstrated strong performance across a wide range of sequence modeling tasks, but their quadratic attention complexity limits scalability to long sequences. Linear models such as Mamba and sliding-window attention (SWA)…
This paper presents switched Multi- Element Antennas (MEAs) as a simple, yet effective, method of enhancing the performance of small cell heterogeneous networks and compensating for the small cell base station sub-optimal placement. The…
Marine seismic exploration is a core technology supporting marine resource exploration, seabed detection, carbon sequestration monitoring, and offshore engineering safety. The integration of full-waveform inversion (FWI), elastic inversion,…
We introduce the SE(3)-Transformer, a variant of the self-attention module for 3D point clouds and graphs, which is equivariant under continuous 3D roto-translations. Equivariance is important to ensure stable and predictable performance in…
Simulating the long-term dynamics of multi-scale and multi-physics systems poses a significant challenge in understanding complex phenomena across science and engineering. The complexity arises from the intricate interactions between scales…
This paper presents a simple and effective method to study the spectral and energy efficiency (SE-EE) trade-off in cellular networks, an issue that has attracted significant recent interest in the wireless community. The proposed…
Accurate direction-of-arrival (DOA) estimation for sound sources is challenging due to the continuous changes in acoustic characteristics across time and frequency. In such scenarios, accurate localization relies on the ability to aggregate…
Floating hybrid wind-wave systems combine offshore wind platforms with wave energy converters (WECs) to create cost-effective and reliable energy solutions. Adequately designed and tuned WECs are essential to avoid unwanted loads disrupting…
Unpaired medical image synthesis aims to provide complementary information for an accurate clinical diagnostics, and address challenges in obtaining aligned multi-modal medical scans. Transformer-based models excel in imaging translation…
The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…
Hyperspectral imaging (HSI) provides rich spectral-spatial information across hundreds of contiguous bands, enabling precise material discrimination in applications such as environmental monitoring, agriculture, and urban analysis. However,…
Simultaneous wireless information and power transfer (SWIPT) provides a promising solution for enabling perpetual wireless networks. As energy efficiency (EE) is an im- portant evaluation of system performance, this thesis studies…