Related papers: The Reflexive Integrated Information Unit: A Diffe…

Reconfigurable Intelligent Surface (RIS) draws great attentions in academic and industry due to its passive and low power consumption nature, and has currently been used in physical layer security to enhance the secure transmission.…

The exponential growth of scientific literature, datasets, and code repositories has created a discovery bottleneck that impedes knowledge synthesis and reproducibility. Traditional dissemination formats -- static PDFs, siloed code hosting,…

We consider a neural network architecture with randomized features, a sign-splitter, followed by rectified linear units (ReLU). We prove that our architecture exhibits robustness to the input perturbation: the output feature of the neural…

Gated recurrent units (GRUs) are specialized memory elements for building recurrent neural networks. Despite their incredible success on various tasks, including extracting dynamics underlying neural data, little is understood about the…

This work presents a novel computer architecture that extends the Von Neumann model with a dedicated Reasoning Unit (RU) to enable native artificial general intelligence capabilities. The RU functions as a specialized co-processor that…

This article introduces S-AI-Recursive, a bio-inspired Sparse Artificial Intelligence architecture in which reasoning is operationalized as a hormonal closed-loop iteration rather than a single feed-forward pass. Building upon the S-AI…

The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. In spite of the impressive success made by transformers in a variety of vision tasks, it still suffers from heavy…

Reconfigurable Intelligent Surfaces (RISs) constitute a promising emerging technology that enables wireless systems to control the propagation environment to enhance diverse communication objectives. To mitigate double-fading attenuation in…

Traditional analytical reflectance models, while compact and interpretable, lack the capacity to accurately represent physical measurements. Recent neural models, which closely fit input data, are less generalizable and often more expensive…

Reconfigurable intelligent surfaces (RISs) not only assist communication but also help the localization of user equipment (UE). This study focuses on the indoor localization of UE with a single access point (AP) aided by multiple RISs.…

The intensive care unit (ICU) is a specialized hospital space where critically ill patients receive intensive care and monitoring. Comprehensive monitoring is imperative in assessing patients conditions, in particular acuity, and ultimately…

Recurrent neural networks have shown remarkable success in modeling sequences. However low resource situations still adversely affect the generalizability of these models. We introduce a new family of models, called Lattice Recurrent Units…

Reconfigurable intelligent surface (RIS)-assisted communication is a key enabling technology for next-generation wireless communication networks, allowing for the reshaping of wireless channels without requiring traditional radio frequency…

Natural data is redundant yet predominant architectures tile computation uniformly across their input and output space. We propose the Recurrent Interface Networks (RINs), an attention-based architecture that decouples its core computation…

Acquiring complex behaviors is essential for artificially intelligent agents, yet learning these behaviors in high-dimensional settings poses a significant challenge due to the vast search space. Traditional reinforcement learning (RL)…

Collective behaviour is known to be the result of diverse dynamics and is sometimes likened to a living system. Although many studies have revealed the dynamics of various collective behaviours, their main focus was on the information…

We demonstrate a novel deep neural network capable of reconstructing human full body pose in real-time from 6 Inertial Measurement Units (IMUs) worn on the user's body. In doing so, we address several difficult challenges. First, the…

The development of artificial intelligence demands that models incrementally update knowledge by Continual Learning (CL) to adapt to open-world environments. To meet privacy and security requirements, Continual Unlearning (CU) emerges as an…

Understanding interaction is an essential part of video action detection. We propose the Asynchronous Interaction Aggregation network (AIA) that leverages different interactions to boost action detection. There are two key designs in it:…

This paper presents a reconfigurable intelligent sensing surface (RISS) that combines passive and active elements to achieve simultaneous reflection and direction of arrival (DOA) estimation tasks. By utilizing DOA information from the RISS…