Related papers: Unlocking Interpretability for RF Sensing: A Compl…

Neurons in auto-regressive language models like GPT-2 can be interpreted by analyzing their activation patterns. Recent studies have shown that techniques such as dictionary learning, a form of post-hoc sparse coding, enhance this…

CRATE, a white-box transformer architecture designed to learn compressed and sparse representations, offers an intriguing alternative to standard vision transformers (ViTs) due to its inherent mathematical interpretability. Despite…

In this paper, we contend that a natural objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a low-dimensional Gaussian mixture supported on incoherent subspaces. The…

Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work \cite{yu2024white} proposed an information-theoretic objective function called Sparse Rate…

Self-supervised depth estimation, which solely requires monocular image sequence as input, has become increasingly popular and promising in recent years. Current research primarily focuses on enhancing the prediction accuracy of the models.…

In this paper, we contend that the objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a mixture of low-dimensional Gaussian distributions supported on incoherent…

Transformer-like models for vision tasks have recently proven effective for a wide range of downstream applications such as segmentation and detection. Previous works have shown that segmentation properties emerge in vision transformers…

In recent years, radio frequency (RF) sensing has gained increasing popularity due to its pervasiveness, low cost, non-intrusiveness, and privacy preservation. However, realizing the promises of RF sensing is highly nontrivial, given…

Wireless sensing, traditionally relying on signal processing (SP) techniques, has recently shifted toward data-driven deep learning (DL) to achieve performance breakthroughs. However, existing deep wireless sensing models are typically…

This paper presents DeepCRF, a new framework that harnesses deep learning to extract subtle micro-signals from channel state information (CSI) measurements, enabling robust and resilient radio-frequency fingerprinting (RFF) of…

As a powerful tool for characterizing cellular subpopulations and cellular heterogeneity, single cell RNA sequencing (scRNA-seq) technology offers advantages of high throughput and multidimensional analysis. However, the process of data…

The explosion of 5G networks and the Internet of Things will result in an exceptionally crowded RF environment, where techniques such as spectrum sharing and dynamic spectrum access will become essential components of the wireless…

Modern edge devices, such as cameras, drones, and Internet-of-Things nodes, rely on deep learning to enable a wide range of intelligent applications, including object recognition, environment perception, and autonomous navigation. However,…

Cognitive Radio (CR) networks presents a paradigm shift aiming to alleviate the spectrum scarcity problem exasperated by the increasing demand on this limited resource. It promotes dynamic spectrum access, cooperation among heterogeneous…

Unlike areas such as computer vision and speech recognition where convolutional and recurrent neural networks-based approaches have proven effective to the nature of the respective areas of application, deep learning (DL) still lacks a…

The analysis of DNA sequences has become critical in numerous fields, from evolutionary biology to understanding gene regulation and disease mechanisms. While deep neural networks can achieve remarkable predictive performance, they…

Deep neural networks are widely used in practical applications of AI, however, their inner structure and complexity made them generally not easily interpretable. Model transparency and interpretability are key requirements for multiple…

This work attempts to provide a plausible theoretical framework that aims to interpret modern deep (convolutional) networks from the principles of data compression and discriminative representation. We argue that for high-dimensional…

Future wireless communication networks are expected to be smarter and more aware of their surroundings, enabling a wide range of context-aware applications. Reconfigurable intelligent surfaces (RISs) are set to play a critical role in…

Spectrum sensing, which aims at detecting spectrum holes, is the precondition for the implementation of cognitive radio (CR). Collaborative spectrum sensing among the cognitive radio nodes is expected to improve the ability of checking…