arXiv subjects

Wei Xu

Publications and source records attributed to Wei Xu.

At least 307 records · Page 17Linked to original sources

arXiv2024

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning

Large language models (LLMs) showcase impressive reasoning capabilities when coupled with Chain-of-Thought (CoT) prompting. However, the robustness of this approach warrants further investigation. In this paper, we introduce a novel scenario termed preemptive answers, where the LLM obtains an answer before engaging in reasoning. This situation can arise inadvertently or induced by malicious users by prompt injection attacks. Experiments reveal that preemptive answers significantly impair the model's reasoning capability across various CoT methods and a broad spectrum of datasets. To bolster the robustness of reasoning, we propose two measures aimed at mitigating this issue to some extent.

cs.CL↗

arXiv2024

Wireless Federated Learning over Resource-Constrained Networks: Digital versus Analog Transmissions

To enable wireless federated learning (FL) in communication resource-constrained networks, two communication schemes, i.e., digital and analog ones, are effective solutions. In this paper, we quantitatively compare these two techniques, highlighting their essential differences as well as respectively suitable scenarios. We first examine both digital and analog transmission schemes, together with a unified and fair comparison framework under imbalanced device sampling, strict latency targets, and transmit power constraints. A universal convergence analysis under various imperfections is established for evaluating the performance of FL over wireless networks. These analytical results reveal that the fundamental difference between the digital and analog communications lies in whether communication and computation are jointly designed or not. The digital scheme decouples the communication design from FL computing tasks, making it difficult to support uplink transmission from massive devices with limited bandwidth and hence the performance is mainly communication-limited. In contrast, the analog communication allows over-the-air computation (AirComp) and achieves better spectrum utilization. However, the computation-oriented analog transmission reduces power efficiency, and its performance is sensitive to computation errors from imperfect channel state information (CSI). Furthermore, device sampling for both schemes are optimized and differences in sampling optimization are analyzed. Numerical results verify the theoretical analysis and affirm the superior performance of the sampling optimization.

cs.IT↗

arXiv2024

Joint MIMO Transceiver and Reflector Design for Reconfigurable Intelligent Surface-Assisted Communication

In this paper, we consider a reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output communication system with multiple antennas at both the base station (BS) and the user. We plan to maximize the achievable rate through jointly optimizing the transmit precoding matrix, the receive combining matrix, and the RIS reflection matrix under the constraints of the transmit power at the BS and the unit-modulus reflection at the RIS. Regarding the non-trivial problem form, we initially reformulate it into an considerable problem to make it tractable by utilizing the relationship between the achievable rate and the weighted minimum mean squared error. Next, the transmit precoding matrix, the receive combining matrix, and the RIS reflection matrix are alternately optimized. In particular, the optimal transmit precoding matrix and receive combining matrix are obtained in closed forms. Furthermore, a pair of computationally efficient methods are proposed for the RIS reflection matrix, namely the semi-definite relaxation (SDR) method and the successive closed form (SCF) method. We theoretically prove that both methods are ensured to converge, and the SCF-based algorithm is able to converges to a Karush-Kuhn-Tucker point of the problem.

cs.IT↗

arXiv2024

The structural-size effect, aging time, and pressure-dependent functional properties of Mn-containing perovskite nanoparticles

The properties of nanoparticles are determined by their size and structure. When exposed to external pressure P, their structural properties can change. The improvement or degradation of the properties of the samples depending on time is particularly interesting. The knowledge of the influence of structural-size effect, aging time, and pressure on the behavior of the compounds is essential for fundamental and applied purposes.Therefore, the first attempts have been made to shed light on how the functional properties of the Mn-containing perovskites change depending on them. The nanoparticles of different sizes, from 20 to 70 nm, have been obtained. After 3 years, their structural properties underwent significant changes, including an increase in particle size, bandwidth, and microstrains, as well as a reduction in dislocation density.The greatest change in the structure is observed for the smallest nanoparticles. The phase transition temperatures increase with nanoparticle size, time, and pressure. The aging time has the strongest influence on the changing Curie temperature for the smallest and most magnetically inhomogeneous nanoparticles with dTc/dP = 100 K / GPa. Conversely, the structural-size effect and external pressure have the greatest influence on the biggest and most magnetically uniform nanoparticles with dTc/dP = 91 and 16 K / GPa, respectively. After 3 years, the biggest nanoparticles demonstrate the most stable phase transition temperatures with improved magnetocaloric parameters near room temperature. These structural-size effect, aging time, and pressure are powerful instruments to tune the phase transition temperatures and magnetocaloric effect of the nanoparticles. These outcomes may have implications for the whole class of perovskites and could initiate a new mainstream.

cond-mat.mtrl-sci↗

arXiv2024

From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers

In this paper, we investigate the inherent capabilities of transformer models in learning arithmetic algorithms, such as addition and parity. Through experiments and attention analysis, we identify a number of crucial factors for achieving optimal length generalization. We show that transformer models are able to generalize to long lengths with the help of targeted attention biasing. In particular, our solution solves the Parity task, a well-known and theoretically proven failure mode for Transformers. We then introduce Attention Bias Calibration (ABC), a calibration stage that enables the model to automatically learn the proper attention biases, which we show to be connected to mechanisms in relative position encoding. We demonstrate that using ABC, the transformer model can achieve unprecedented near-perfect length generalization on certain arithmetic tasks. In addition, we show that ABC bears remarkable similarities to RPE and LoRA, which may indicate the potential for applications to more complex tasks.

cs.LG↗

arXiv2024

A Joint Communication and Computation Design for Distributed RISs Assisted Probabilistic Semantic Communication in IIoT

In this paper, the problem of spectral-efficient communication and computation resource allocation for distributed reconfigurable intelligent surfaces (RISs) assisted probabilistic semantic communication (PSC) in industrial Internet-of-Things (IIoT) is investigated. In the considered model, multiple RISs are deployed to serve multiple users, while PSC adopts compute-then-transmit protocol to reduce the transmission data size. To support high-rate transmission, the semantic compression ratio, transmit power allocation, and distributed RISs deployment must be jointly considered. This joint communication and computation problem is formulated as an optimization problem whose goal is to maximize the sum semantic-aware transmission rate of the system under total transmit power, phase shift, RIS-user association, and semantic compression ratio constraints. To solve this problem, a many-to-many matching scheme is proposed to solve the RIS-user association subproblem, the semantic compression ratio subproblem is addressed following greedy policy, while the phase shift of RIS can be optimized using the tensor based beamforming. Numerical results verify the superiority of the proposed algorithm.

cs.IT↗

arXiv2024

Unlocking Potentials of Near-Field Propagation: ELAA-Empowered Integrated Sensing and Communication

The exploration of extremely large antenna arrays (ELAAs) using high-frequency spectrum has led to a paradigm shift in electromagnetic radiation field, transitioning from the common use case of far-field propagation to near-field propagation. This shift necessitates the modification of the conventional planar-wavefront approximation to more accurate spherical waves, exerting a profound impact on wireless transmission technologies encompassing communication and sensing. Concurrently, integrated sensing and communication (ISAC) has gained prominence in the context of the sixth-generation (6G) wireless networks owing to its ability to cater to the ever-increasing demands of future networks. In line with this evolving trend, this article presents a systematical investigation on ELAA-empowered near-field ISAC. We begin by introducing the fundamentals of near-field propagation with an emphasis on its double-edged effects to near-field communications. Then, we turn to near-field sensing and expound upon various typical applications. Following the separate elaborations on communications and sensing, we articulate in-depth advantages of ELAA-empowered ISAC in near field, particularly including featured opportunities arising from the dual-functional integrations, potential ISAC applications benefiting from the additional degrees-of-freedom in near field, and enablements of other complementary technologies. Finally, we outline key technical challenges that merit further exploration in the realm of ELAA-empowered near-field ISAC.

cs.IT↗

arXiv2024

Learning Wireless Data Knowledge Graph for Green Intelligent Communications: Methodology and Experiments

Intelligent communications have played a pivotal role in shaping the evolution of 6G networks. Native artificial intelligence (AI) within green communication systems must meet stringent real-time requirements. To achieve this, deploying lightweight and resource-efficient AI models is necessary. However, as wireless networks generate a multitude of data fields and indicators during operation, only a fraction of them imposes significant impact on the network AI models. Therefore, real-time intelligence of communication systems heavily relies on a small but critical set of the data that profoundly influences the performance of network AI models. These challenges underscore the need for innovative architectures and solutions. In this paper, we propose a solution, termed the pervasive multi-level (PML) native AI architecture, which integrates the concept of knowledge graph (KG) into the intelligent operational manipulations of mobile networks, resulting in the establishment of a wireless data KG. Leveraging the wireless data KG, we characterize the massive and complex data collected from wireless communication networks and analyze the relationships among various data fields. The obtained graph of data field relations enables the on-demand generation of minimal and effective datasets, referred to as feature datasets, tailored to specific application requirements. Consequently, this architecture not only enhances AI training, inference, and validation processes but also significantly reduces resource wastage and overhead for communication networks. To implement this architecture, we have developed a specific solution comprising a spatio-temporal heterogeneous graph attention neural network model (STREAM) as well as a feature dataset generation algorithm. Experiments are conducted to validate the effectiveness of the proposed architecture.

cs.NI↗

arXiv2024

Trainable Joint Channel Estimation, Detection and Decoding for MIMO URLLC Systems

The receiver design for multi-input multi-output (MIMO) ultra-reliable and low-latency communication (URLLC) systems can be a tough task due to the use of short channel codes and few pilot symbols. Consequently, error propagation can occur in traditional turbo receivers, leading to performance degradation. Moreover, the processing delay induced by information exchange between different modules may also be undesirable for URLLC. To address the issues, we advocate to perform joint channel estimation, detection, and decoding (JCDD) for MIMO URLLC systems encoded by short low-density parity-check (LDPC) codes. Specifically, we develop two novel JCDD problem formulations based on the maximum a posteriori (MAP) criterion for Gaussian MIMO channels and sparse mmWave MIMO channels, respectively, which integrate the pilots, the bit-to-symbol mapping, the LDPC code constraints, as well as the channel statistical information. Both the challenging large-scale non-convex problems are then solved based on the alternating direction method of multipliers (ADMM) algorithms, where closed-form solutions are achieved in each ADMM iteration. Furthermore, two JCDD neural networks, called JCDDNet-G and JCDDNet-S, are built by unfolding the derived ADMM algorithms and introducing trainable parameters. It is interesting to find via simulations that the proposed trainable JCDD receivers can outperform the turbo receivers with affordable computational complexities.

eess.SP↗

arXiv2024

Studying the Impact of Latent Representations in Implicit Neural Networks for Scientific Continuous Field Reconstruction

Learning a continuous and reliable representation of physical fields from sparse sampling is challenging and it affects diverse scientific disciplines. In a recent work, we present a novel model called MMGN (Multiplicative and Modulated Gabor Network) with implicit neural networks. In this work, we design additional studies leveraging explainability methods to complement the previous experiments and further enhance the understanding of latent representations generated by the model. The adopted methods are general enough to be leveraged for any latent space inspection. Preliminary results demonstrate the contextual information incorporated in the latent representations and their impact on the model performance. As a work in progress, we will continue to verify our findings and develop novel explainability approaches.

cs.LG↗

arXiv2024

Spatially Correlated RIS-Aided Secure Massive MIMO Under CSI and Hardware Imperfections

This paper investigates the integration of a reconfigurable intelligent surface (RIS) into a secure multiuser massive multiple-input multiple-output (MIMO) system in the presence of transceiver hardware impairments (HWI), imperfect channel state information (CSI), and spatially correlated channels. We first introduce a linear minimum-mean-square error estimation algorithm for the aggregate channel by considering the impact of transceiver HWI and RIS phase-shift errors. Then, we derive a lower bound for the achievable ergodic secrecy rate in the presence of a multi-antenna eavesdropper when artificial noise (AN) is employed at the base station (BS). In addition, the obtained expressions of the ergodic secrecy rate are further simplified in some noteworthy special cases to obtain valuable insights. To counteract the effects of HWI, we present a power allocation optimization strategy between the confidential signals and AN, which admits a fixed-point equation solution. Our analysis reveals that a non-zero ergodic secrecy rate is preserved if the total transmit power decreases no faster than $1/N$, where $N$ is the number of RIS elements. Moreover, the ergodic secrecy rate grows logarithmically with the number of BS antennas $M$ and approaches a certain limit in the asymptotic regime $N\rightarrow\infty$. Simulation results are provided to verify the derived analytical results. They reveal the impact of key design parameters on the secrecy rate. It is shown that, with the proposed power allocation strategy, the secrecy rate loss due to HWI can be counteracted by increasing the number of low-cost RIS elements.

cs.IT↗

arXiv2024

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis

Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is inefficient as it relies on high computational costs (e.g., training GPU memory) and massive storage space. In this paper, we aim to study parameter-efficient transfer learning for point cloud analysis with an ideal trade-off between task performance and parameter efficiency. To achieve this goal, we freeze the parameters of the default pre-trained models and then propose the Dynamic Adapter, which generates a dynamic scale for each token, considering the token significance to the downstream task. We further seamlessly integrate Dynamic Adapter with Prompt Tuning (DAPT) by constructing Internal Prompts, capturing the instance-specific features for interaction. Extensive experiments conducted on five challenging datasets demonstrate that the proposed DAPT achieves superior performance compared to the full fine-tuning counterparts while significantly reducing the trainable parameters and training GPU memory by 95% and 35%, respectively. Code is available at https://github.com/LMD0311/DAPT.

cs.CV↗

arXiv2024

Joint Training and Reflection Pattern Optimization for Non-Ideal RIS-Aided Multiuser Systems

Reconfigurable intelligent surface (RIS) is a promising technique to improve the performance of future wireless communication systems at low energy consumption. To reap the potential benefits of RIS-aided beamforming, it is vital to enhance the accuracy of channel estimation. In this paper, we consider an RIS-aided multiuser system with non-ideal reflecting elements, each of which has a phase-dependent reflecting amplitude, and we aim to minimize the mean-squared error (MSE) of the channel estimation by jointly optimizing the training signals at the user equipments (UEs) and the reflection pattern at the RIS. As examples the least squares (LS) and linear minimum MSE (LMMSE) estimators are considered. The considered problems do not admit simple solution mainly due to the complicated constraints pertaining to the non-ideal RIS reflecting elements. As far as the LS criterion is concerned, we tackle this difficulty by first proving the optimality of orthogonal training symbols and then propose a majorization-minimization (MM)-based iterative method to design the reflection pattern, where a semi-closed form solution is obtained in each iteration. As for the LMMSE criterion, we address the joint training and reflection pattern optimization problem with an MM-based alternating algorithm, where a closed-form solution to the training symbols and a semi-closed form solution to the RIS reflecting coefficients are derived, respectively. Furthermore, an acceleration scheme is proposed to improve the convergence rate of the proposed MM algorithms. Finally, simulation results demonstrate the performance advantages of our proposed joint training and reflection pattern designs.

cs.IT↗

arXiv2024

Purposeful remixing with generative AI: Constructing designer voice in multimodal composing

Voice, the discursive construction of the writer's identity, has been extensively studied and theorized in composition studies. In multimodal writing, students are able to mobilize both linguistic and non linguistic resources to express their real or imagined identities. But at the same time, when students are limited to choose from available online resources, their voices might be compromised due to the incompatibility between their authorial intentions and the existing materials. This study, therefore, investigates whether the use of generative AI tools could help student authors construct a more consistent voice in multimodal writing. In this study, we have designed a photo essay assignment where students recount a story in the form of photo essays and prompt AI image generating tools to create photos for their storytelling. Drawing on interview data, written reflection, written annotation, and multimodal products from seven focal participants, we have identified two remixing practices, through which students attempted to establish a coherent and unique voice in writing. The study sheds light on the intentional and discursive nature of multimodal writing with AI as afforded by the technological flexibility, while also highlighting the practical and ethical challenges that could be attributed to students insufficient prompt and multimodal literacy and the innate limitations of AI systems. This study provides important implications for incorporating AI tools in designing multimodal writing tasks.

cs.CY↗

arXiv2024

Deep CSI Compression for Dual-Polarized Massive MIMO Channels with Disentangled Representation Learning

Channel state information (CSI) feedback is critical for achieving the promised advantages of enhancing spectral and energy efficiencies in massive multiple-input multiple-output (MIMO) wireless communication systems. Deep learning (DL)-based methods have been proven effective in reducing the required signaling overhead for CSI feedback. In practical dual-polarized MIMO scenarios, channels in the vertical and horizontal polarization directions tend to exhibit high polarization correlation. To fully exploit the inherent propagation similarity within dual-polarized channels, we propose a disentangled representation neural network (NN) for CSI feedback, referred to as DiReNet. The proposed DiReNet disentangles dual-polarized CSI into three components: polarization-shared information, vertical polarization-specific information, and horizontal polarization-specific information. This disentanglement of dual-polarized CSI enables the minimization of information redundancy caused by the polarization correlation and improves the performance of CSI compression and recovery. Additionally, flexible quantization and network extension schemes are designed. Consequently, our method provides a pragmatic solution for CSI feedback to harness the physical MIMO polarization as a priori information. Our experimental results show that the performance of our proposed DiReNet surpasses that of existing DL-based networks, while also effectively reducing the number of network parameters by nearly one third.

cs.IT↗

arXiv2024

Secure Outage Analysis for RIS-Aided MISO Systems with Randomly Located Eavesdroppers

In this paper, we consider the physical layer security of an RIS-assisted multiple-antenna communication system with randomly located eavesdroppers. The exact distributions of the received signal-to-noise-ratios (SNRs) at the legitimate user and the eavesdroppers located according to a Poisson point process (PPP) are derived, and a closed-form expression for the secrecy outage probability (SOP) is obtained. It is revealed that the secrecy performance is mainly affected by the number of RIS reflecting elements, and the impact of the transmit antennas and transmit power at the base station is marginal. In addition, when the locations of the randomly located eavesdroppers are unknown, deploying the RIS closer to the legitimate user rather than to the base station is shown to be more efficient. We also perform an analytical study demonstrating that the secrecy diversity order depends on the path loss exponent of the RIS-to-ground links. Finally, numerical simulations are conducted to verify the accuracy of these theoretical observations.

cs.IT↗

arXiv2024

On Secrecy Performance of RIS-Assisted MISO Systems over Rician Channels with Spatially Random Eavesdroppers

Reconfigurable intelligent surface (RIS) technology is emerging as a promising technique for performance enhancement for next-generation wireless networks. This paper investigates the physical layer security of an RIS-assisted multiple-antenna communication system in the presence of random spatially distributed eavesdroppers. The RIS-to-ground channels are assumed to experience Rician fading. Using stochastic geometry, exact distributions of the received signal-to-noise-ratios (SNRs) at the legitimate user and the eavesdroppers located according to a Poisson point process (PPP) are derived, and closed-form expressions for the secrecy outage probability (SOP) and the ergodic secrecy capacity (ESC) are obtained to provide insightful guidelines for system design. First, the secrecy diversity order is obtained as $\frac{2}{α_2}$, where $α_2$ denotes the path loss exponent of the RIS-to-ground links. Then, it is revealed that the secrecy performance is mainly affected by the number of RIS reflecting elements, $N$, and the impact of the number of transmit antennas and transmit power at the base station is marginal. In addition, when the locations of the randomly located eavesdroppers are unknown, deploying the RIS closer to the legitimate user rather than to the base station is shown to be more efficient. Moreover, it is also found that the density of randomly located eavesdroppers, $λ_e$, has an additive effect on the asymptotic ESC performance given by $\log_2{\left({1}/{λ_e}\right)}$. Finally, numerical simulations are conducted to verify the accuracy of these theoretical observations.

cs.IT↗

arXiv2024

Having Beer after Prayer? Measuring Cultural Bias in Large Language Models

As the reach of large language models (LMs) expands globally, their ability to cater to diverse cultural contexts becomes crucial. Despite advancements in multilingual capabilities, models are not designed with appropriate cultural nuances. In this paper, we show that multilingual and Arabic monolingual LMs exhibit bias towards entities associated with Western culture. We introduce CAMeL, a novel resource of 628 naturally-occurring prompts and 20,368 entities spanning eight types that contrast Arab and Western cultures. CAMeL provides a foundation for measuring cultural biases in LMs through both extrinsic and intrinsic evaluations. Using CAMeL, we examine the cross-cultural performance in Arabic of 16 different LMs on tasks such as story generation, NER, and sentiment analysis, where we find concerning cases of stereotyping and cultural unfairness. We further test their text-infilling performance, revealing the incapability of appropriate adaptation to Arab cultural contexts. Finally, we analyze 6 Arabic pre-training corpora and find that commonly used sources such as Wikipedia may not be best suited to build culturally aware LMs, if used as they are without adjustment. We will make CAMeL publicly available at: https://github.com/tareknaous/camel

cs.CL↗