Search

To explore the full potential of ultra-massive multiple-input multiple-output (MIMO) communication systems, it is fundamental to understand new ultra-massive MIMO channel characteristics and establish pervasive channel models. On this basis, large dimensional spatial-temporal transmission and random access technologies need to be investigated and evaluated for better practical implementation. Firstly, this paper reviews recent advances of ultra-massive MIMO technologies in the traditional spatial domain, including wireless channel characterization and modeling, channel estimation, spatial multiplexing, and precoding. Secondly, considering the dramatic increase of base station (BS) antennas and access users in ultra-massive MIMO systems, the confronted high dimensional complexity and computing burden of these ultra-massive MIMO technologies are indicated. To provide efficient and systematic solution, the emerging tendency to transform related technologies from the traditional spatial domain to beam domain is introduced. The utilities of large sparsity merit, reduced energy consumption, and improved usage of radio frequency (RF) chains in the beam domain channel are elaborated. At last, future challenges of ultra-massive MIMO communication systems are discussed.

It is envisioned that the sixth generation (6G) and beyond 6G (B6G) wireless communication networks will enable global coverage in space, air, ground, and sea. In this case, both base stations and users can be mobile and will tend to move continuously in three-dimensional (3D) space. Therefore, obtaining channel state information (CSI) in 3D continuous-space is crucial for the design and performance evaluation of future 6G and B6G wireless systems. On the other hand, new 6G technologies such as integrated sensing and communications (ISAC) will also require prior knowledge of CSI in 3D continuous-space. In this paper, a 3D continuous-space electromagnetic channel model is proposed for tri-polarized multi-user communications, taking into account scatterers and spherical wavefronts. Scattered fields are calculated using the method of moments (MoM) with high accuracy. Spherical wave functions are utilized to decompose the dyadic Green's functions that connect the transmitted source currents and the received electric fields. Simulation results demonstrate that transmit power, apertures, scatterers, and sample intervals have significant impacts on statistical properties and channel capacities, providing insights into the performance of continuous-space electromagnetic channel models and the design of future wireless systems.

Wireless Fidelity (Wi-Fi) communication technologies hold significant potential for realizing the Industrial Internet of Things (IIoT). In this paper, both Single-Input Single-Output (SISO) and polarized Multiple-Input Multiple-Output (MIMO) channel measurements are conducted in an IIoT scenario at the less congested Wi-Fi band, i.e., 5.5~GHz. The purpose is to investigate wireless characteristics of communications between access points and terminals mounted on automated guided vehicles as well as those surrounding manufacturing areas. For SISO channel measurements, statistical properties including the delay Power Spectral Density (PSD), path loss, shadowing fading, delay spread, excess delay, K-factor, and amplitude distribution of small-scale fading are analyzed and compared with those observed in an office scenario. For MIMO channel measurements, results show that there are multiple Dense Multipath Component (DMC) processes in the delay PSD. An estimation algorithm based on the algorithm for a single DMC process is proposed to effectively process the multi-processes data. Moreover, delay, angular, power, and polarization properties of DMCs are investigated and compared with those of specular multipath components. Furthermore, effects of DMCs on Singular Values (SVs) and channel capacities are explored. Ignoring DMCs can overestimate SVs and underestimate channel capacities.

In massive multiple-input multiple-output (MIMO) systems, the channel estimation scheme is subject to the spatial non-stationarity and inevitably power leakage in the beam domain. In this paper, a beam domain channel estimation scheme is investigated for spatial non-stationary (SNS) massive MIMO systems considering power leakage. %a novel beam domain channel estimation scheme is proposed for spatial non-stationary (SNS) massive MIMO systems. Specifically, a realistic massive MIMO beam domain channel model (BDCM) is introduced to capture the spatial non-stationarity considering power leakage by introducing the illustration of visibility region (VR). Then, a beam domain structure-based sparsity adaptive matching pursuit (BDS-SAMP) scheme is proposed based on the cross-block sparse structure and power ratio threshold of beam domain channel. Finally, the simulation results validate the accuracy of proposed BDS-SAMP scheme with low pilot overhead and reasonable complexity by comparing with conventional schemes.

The performance evaluation of sixth generation (6G) communication systems is anticipated to be a controlled and repeatable process in the lab, which brings up the demand for wireless channel emulators. However, channel emulation for 6G space-time-frequency (STF) non-stationary channels is missing currently. In this paper, a non-stationary multiple-input multiple-output (MIMO) geometry-based stochastic model (GBSM) that accurately characterizes the channel STF properties is introduced firstly. Then, a subspace-based method is proposed for reconstructing the channel fading obtained from the GBSM and a channel emulator architecture with frequency domain processing is presented for 6G MIMO systems. Moreover, the spatial time-varying channel transfer functions (CTFs) of the channel simulation and the channel emulation are compared and analyzed. The Doppler power spectral density (PSD) and delay PSD are further derived and compared between the channel model simulation and subspace-based emulation. The results demonstrate that the proposed channel emulator is capable of reproducing the non-stationary channel characteristics.

Based on the vision of global coverage for sixth-generation (6G) wireless communication systems, the low earth orbit (LEO) satellite-to-ground channel model for urban scenarios has emerged as highly important for the system design. In this paper, we propose an LEO satellite-to-ground channel model through shooting and bouncing rays (SBR) algorithm to analyze the channel characteristics. The orbit of LEO is modeled by the simplified general perturbations 4 (SGP4), and an accurate celestial model is applied to calculate the Doppler shift of multipath in a transmission time window of LEO satellite-to-ground communications. Channel characteristics of LEO satellite-to-ground communications such as the root-mean-square (RMS) delay spread, the Doppler shift, and the received power at different times are obtained. The simulation results show that the received power is only significantly noticeable in the transmission time window when the satellite is close to the receiver. Proposed model validates the effectiveness of ray-tracing in actual LEO satellite-to-ground communication scenarios and extends the calculation of the Doppler shift.

The ray-tracing is often employed in urban areas for channel modeling with high accuracy but encounters a substantial computational complexity for high mobility scenarios. In this paper, we propose a novel pre-processing method for dynamic ray-tracing to reduce the computational burden in high-mobility scenarios by prepending the intersection judgment to the pre-processing stage. The proposed method generates an inter-visibility matrix that establishes visibility relationships among static objects in the environment considering the intersection judgment. Moreover, the inter-visibility matrix can be employed to create the inter-visibility table for mobile transmitters and receivers, which can improve the efficiency of constructing an image tree for the three-dimensional (3D) dynamic ray-tracing method. The results show that the proposed pre-processing method in dynamic ray-tracing has considerable time-saving compared with the traditional method while maintaining the same accuracy. The channel characteristics computed by the proposed method can well match to the channel measurements.

Given an analytic function $f=u+iv$ in the unit disk $\mathbb{D}$, Zygmund's theorem gives the minimal growth restriction on $u$ which ensures that $v$ is in the Hardy space $h^1$. This need not be true if $f$ is a complex-valued harmonic function. However, we prove that Zygmund's theorem holds if $f$ is a harmonic $K$-quasiregular mapping in $\ID$. Our work makes further progress on the recent Riesz-type theorem of Liu and Zhu (Adv. Math., 2023), and the Kolmogorov-type theorem of Kalaj (J. Math. Anal. Appl., 2025), for harmonic quasiregular mappings. We also obtain a partial converse, thus showing that the proposed growth condition is the best possible. Furthermore, as an application of the classical conjugate function theorems, we establish a harmonic analogue of a well-known result of Hardy and Littlewood., Comment: 12 pages

Human-centric perceptions play a crucial role in real-world applications. While recent human-centric works have achieved impressive progress, these efforts are often constrained to the visual domain and lack interaction with human instructions, limiting their applicability in broader scenarios such as chatbots and sports analysis. This paper introduces Referring Human Perceptions, where a referring prompt specifies the person of interest in an image. To tackle the new task, we propose RefHCM (Referring Human-Centric Model), a unified framework to integrate a wide range of human-centric referring tasks. Specifically, RefHCM employs sequence mergers to convert raw multimodal data -- including images, text, coordinates, and parsing maps -- into semantic tokens. This standardized representation enables RefHCM to reformulate diverse human-centric referring tasks into a sequence-to-sequence paradigm, solved using a plain encoder-decoder transformer architecture. Benefiting from a unified learning strategy, RefHCM effectively facilitates knowledge transfer across tasks and exhibits unforeseen capabilities in handling complex reasoning. This work represents the first attempt to address referring human perceptions with a general-purpose framework, while simultaneously establishing a corresponding benchmark that sets new standards for the field. Extensive experiments showcase RefHCM's competitive and even superior performance across multiple human-centric referring tasks. The code and data are publicly at https://github.com/JJJYmmm/RefHCM., Comment: 13 pages

With the rapid development of multimedia, the shift from unimodal textual sentiment analysis to multimodal image-text sentiment analysis has obtained academic and industrial attention in recent years. However, multimodal sentiment analysis is affected by unimodal data bias, e.g., text sentiment is misleading due to explicit sentiment semantic, leading to low accuracy in the final sentiment classification. In this paper, we propose a novel CounterFactual Multimodal Sentiment Analysis framework (CF-MSA) using causal counterfactual inference to construct multimodal sentiment causal inference. CF-MSA mitigates the direct effect from unimodal bias and ensures heterogeneity across modalities by differentiating the treatment variables between modalities. In addition, considering the information complementarity and bias differences between modalities, we propose a new optimisation objective to effectively integrate different modalities and reduce the inherent bias from each modality. Experimental results on two public datasets, MVSA-Single and MVSA-Multiple, demonstrate that the proposed CF-MSA has superior debiasing capability and achieves new state-of-the-art performances. We will release the code and datasets to facilitate future research.

Network data packet anomaly detection faces numerous challenges, including exploring new anomaly supervision signals, researching weakly supervised anomaly detection, and improving model interpretability. This paper proposes NIDS-GPT, a GPT-based causal language model for network intrusion detection. Unlike previous work, NIDS-GPT innovatively treats each number in the packet as an independent "word" rather than packet fields, enabling a more fine-grained data representation. We adopt an improved GPT-2 model and design special tokenizers and embedding layers to better capture the structure and semantics of network data. NIDS-GPT has good scalability, supports unsupervised pre-training, and enhances model interpretability through attention weight visualization. Experiments on the CICIDS2017 and car-hacking datasets show that NIDS-GPT achieves 100\% accuracy under extreme imbalance conditions, far surpassing traditional methods; it also achieves over 90\% accuracy in one-shot learning. These results demonstrate NIDS-GPT's excellent performance and potential in handling complex network anomaly detection tasks, especially in data-imbalanced and resource-constrained scenarios. The code is available at \url{https://github.com/woshixiaobai2019/nids-gpt.gi

In this paper, we study the problem of the distributed Nash equilibrium seeking of N-player games over jointly strongly connected switching networks. The action of each player is governed by a class of uncertain nonlinear systems. Our approach integrates the consensus algorithm, the distributed estimator over jointly strongly connected switching networks, and some adaptive control technique. Furthermore, we also consider the disturbance rejection problem for bounded disturbances with unknown bounds. A special case of our results gives the solution of the distributed Nash equilibrium seeking for high-order integrator systems., Comment: 7 pages

In this paper, we first study the leader-following output synchronization problem for a class of uncertain nonlinear multi-agent systems over jointly connected switching networks. Our approach integrates the output-based adaptive distributed observer, the conventional adaptive control technique, and the output regulation theory. Compared with the existing results, our control law only relies on the output of the leader instead of the state of the leader and allows the followers and the leader to have different orders. Then, we further consider the rejection of a class of bounded disturbances with unknown bounds. Our problem includes the state consensus problem as a special case if the followers and the leader have the same order., Comment: 7 pages

The data-driven techniques have been developed to deal with the output regulation problem of unknown linear systems by various approaches. In this paper, we first extend an existing algorithm from single-input single-output linear systems to multi-input multi-output linear systems. Then, by separating the dynamics used in the learning phase and the control phase, we further propose an improved algorithm that significantly reduces the computational cost and weakens the solvability conditions over the first algorithm.

We introduce SimulBench, a benchmark designed to evaluate large language models (LLMs) across a diverse collection of creative simulation scenarios, such as acting as a Linux terminal or playing text games with users. While these simulation tasks serve as effective measures of an LLM's general intelligence, they are seldom incorporated into existing benchmarks. A major challenge is to develop an evaluation framework for testing different LLMs fairly while preserving the multi-round interactive nature of simulation tasks between users and AI. To tackle this issue, we suggest using a fixed LLM as a user agent to engage with an LLM to collect dialogues first under different tasks. Then, challenging dialogue scripts are extracted for evaluating different target LLMs. To facilitate automatic assessment on \DataName{}, GPT-4 is employed as the evaluator, tasked with reviewing the quality of the final response generated by the target LLMs given multi-turn dialogue scripts. Our comprehensive experiments indicate that these simulation tasks continue to pose a significant challenge with their unique natures and show the gap between proprietary models and the most advanced open LLMs. For example, GPT-4-turbo outperforms LLaMA-3-70b-Chat on 18.55\% more cases., Comment: Website: https://simulbench.github.io/

In a series of papers, we have proposed a non-perturbative field-theoretic approach to deal with strong electron-phonon and strong Coulomb interactions. The key ingredient of such an approach is to determine the full fermion-boson vertex corrections by solving a number of self-consistent Ward-Takahashi identities. Palle (see Phys. Rev. B 110, 026501 (2024), arXiv:2404.02918) argued that our Ward-Takahashi identities failed to include some important additional terms and thus are incorrect. We agree that our Ward-Takahashi identities have ignored some potentially important contributions and here give some remarks on the role played by the additional terms., Comment: Reply to arXiv:2404.02918, which is published as Phys. Rev. B 110, 026501 (2024), by Palle, commenting on arXiv:1911.05528

The recently proposed Segment Anything Model (SAM) is a general tool for image segmentation, but it requires additional adaptation and careful fine-tuning for medical image segmentation, especially for small, irregularly-shaped, and boundary-ambiguous anatomical structures such as the knee cartilage that is of interest in this work. Repaired cartilage, after certain surgical procedures, exhibits imaging patterns unseen to pre-training, posing further challenges for using models like SAM with or without general-purpose fine-tuning. To address this, we propose a novel registration-based prompt engineering framework for medical image segmentation using SAM. This approach utilises established image registration algorithms to align the new image (to-be-segmented) and a small number of reference images, without requiring segmentation labels. The spatial transformations generated by registration align either the new image or pre-defined point-based prompts, before using them as input to SAM. This strategy, requiring as few as five reference images with defined point prompts, effectively prompts SAM for inference on new images, without needing any segmentation labels. Evaluation of MR images from patients who received cartilage stem cell therapy yielded Dice scores of 0.89, 0.87, 0.53, and 0.52 for segmenting femur, tibia, femoral- and tibial cartilages, respectively. This outperforms atlas-based label fusion and is comparable to supervised nnUNet, an upper-bound fair baseline in this application, both of which require full segmentation labels for reference samples. The codes are available at: https://github.com/chrissyinreallife/KneeSegmentWithSAM.git, Comment: Accepted to the 11th International Workshop on Biomedical Image Registration (WBIR 2024)

Single image super-resolution (SR) is an established pixel-level vision task aimed at reconstructing a high-resolution image from its degraded low-resolution counterpart. Despite the notable advancements achieved by leveraging deep neural networks for SR, most existing deep learning architectures feature an extensive number of layers, leading to high computational complexity and substantial memory demands. These issues become particularly pronounced in the context of infrared image SR, where infrared devices often have stringent storage and computational constraints. To mitigate these challenges, we introduce a novel, efficient, and precise single infrared image SR model, termed the Lightweight Information Split Network (LISN). The LISN comprises four main components: shallow feature extraction, deep feature extraction, dense feature fusion, and high-resolution infrared image reconstruction. A key innovation within this model is the introduction of the Lightweight Information Split Block (LISB) for deep feature extraction. The LISB employs a sequential process to extract hierarchical features, which are then aggregated based on the relevance of the features under consideration. By integrating channel splitting and shift operations, the LISB successfully strikes an optimal balance between enhanced SR performance and a lightweight framework. Comprehensive experimental evaluations reveal that the proposed LISN achieves superior performance over contemporary state-of-the-art methods in terms of both SR quality and model complexity, affirming its efficacy for practical deployment in resource-constrained infrared imaging applications.

The problem of the distributed Nash equilibrium seeking for aggregative games has been studied over strongly connected and weight-balanced static networks and every time strongly connected and weight-balanced switching networks. In this paper, we further study the same problem over jointly connected and weight-balanced networks. The existing approaches critically rely on the connectedness of the network for constructing a Lyapunov function for their algorithms and theses approaches fail if the network is not connected. To overcome this difficulty, we propose an approach to show the exponential convergence of the output of the closed-loop system to the unknown Nash equilibrium (NE) point under a set of mild conditions.

Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user's preferred response length (recall). Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality. LongFact, SAFE, and all experimental code are available at https://github.com/google-deepmind/long-form-factuality., Comment: NeurIPS 2024; 72 pages, 18 figures, 30 tables. Code at https://github.com/google-deepmind/long-form-factuality

Large Language Models (LLMs) have become integral components in various autonomous agent systems. In this study, we present an exploration-based trajectory optimization approach, referred to as ETO. This learning method is designed to enhance the performance of open LLM agents. Contrary to previous studies that exclusively train on successful expert trajectories, our method allows agents to learn from their exploration failures. This leads to improved performance through an iterative optimization framework. During the exploration phase, the agent interacts with the environment while completing given tasks, gathering failure trajectories to create contrastive trajectory pairs. In the subsequent training phase, the agent utilizes these trajectory preference pairs to update its policy using contrastive learning methods like DPO. This iterative cycle of exploration and training fosters continued improvement in the agents. Our experiments on three complex tasks demonstrate that ETO consistently surpasses baseline performance by a large margin. Furthermore, an examination of task-solving efficiency and potential in scenarios lacking expert trajectory underscores the effectiveness of our approach., Comment: Accepted to ACL 2024 Main Conference; Camera Ready