Enhancing CoMP-RSMA Performance with Movable Antennas: A Meta-Learning Optimization Framework

This study investigates a downlink rate-splitting multiple access (RSMA) scenario in which multiple base stations (BSs), employing a coordinated multi-point (CoMP) transmission scheme, serve users equipped with movable antenna (MA) technology. Unlike traditional fixed-position antennas (FPAs), which are subject to random variations in wireless channels, MAs can be strategically repositioned to locations with more favorable channel conditions, thereby achieving enhanced spatial diversity gains.To leverage these advantages and maximize the achievable sum rate, we formulate an optimization problem that jointly determines the optimal transmit beamforming vectors at the BSs, the common stream allocation for different users, and the optimal positioning of the MAs, all while ensuring compliance with quality of service (QoS) constraints. However, the formulated problem is non-convex and computationally challenging due to the strong interdependence among the optimization variables. Traditional methods for solving large-scale optimization problems typically incur prohibitively high computational complexity. To address the above challenge, we propose a gradient-based meta-learning (GML) algorithm that operates without pre-training and is well-suited for handling large-scale optimization tasks. Numerical results demonstrate the effectiveness and accuracy of the proposed approach, achieving near-optimal performance (exceeding 97% compared to the optimal solution). Moreover, the MA-enabled CoMP-RSMA model significantly outperforms conventional benchmark schemes, yielding performance gains of up to 190% over the spatial division multiple access (SDMA) scheme and 80% over the RSMA FPA-based model. Finally, the proposed approach is shown to mitigate the sum-rate limitations imposed by interference in SDMA, achieving superior performance with fewer BSs.

MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion

Despite the remarkable capabilities of large language models across various tasks, their continued scaling faces a critical challenge: the scarcity of high-quality pretraining data. While model architectures continue to evolve, the natural language data struggles to scale up. To tackle this bottleneck, we propose \textbf{MA}ssive \textbf{G}enre-\textbf{A}udience~(MAGA) reformulation method, which systematic synthesizes diverse, contextually-rich pretraining data from existing corpus. This work makes three main contributions: (1) We propose MAGA reformulation method, a lightweight and scalable approach for pretraining corpus expansion, and build a 770B tokens MAGACorpus. (2) We evaluate MAGACorpus with different data budget scaling strategies, demonstrating consistent improvements across various model sizes (134M-13B), establishing the necessity for next-generation large-scale synthetic pretraining language models. (3) Through comprehensive analysis, we investigate prompt engineering's impact on synthetic training collapse and reveal limitations in conventional collapse detection metrics using validation losses. Our work shows that MAGA can substantially expand training datasets while maintaining quality, offering a reliably pathway for scaling models beyond data limitations.

Human Decision-making is Susceptible to AI-driven Manipulation

Artificial Intelligence (AI) systems are increasingly intertwined with daily life, assisting users in executing various tasks and providing guidance on decision-making. This integration introduces risks of AI-driven manipulation, where such systems may exploit users' cognitive biases and emotional vulnerabilities to steer them toward harmful outcomes. Through a randomized controlled trial with 233 participants, we examined human susceptibility to such manipulation in financial (e.g., purchases) and emotional (e.g., conflict resolution) decision-making contexts. Participants interacted with one of three AI agents: a neutral agent (NA) optimizing for user benefit without explicit influence, a manipulative agent (MA) designed to covertly influence beliefs and behaviors, or a strategy-enhanced manipulative agent (SEMA) employing explicit psychological tactics to reach its hidden objectives. By analyzing participants' decision patterns and shifts in their preference ratings post-interaction, we found significant susceptibility to AI-driven manipulation. Particularly, across both decision-making domains, participants interacting with the manipulative agents shifted toward harmful options at substantially higher rates (financial, MA: 62.3%, SEMA: 59.6%; emotional, MA: 42.3%, SEMA: 41.5%) compared to the NA group (financial, 35.8%; emotional, 12.8%). Notably, our findings reveal that even subtle manipulative objectives (MA) can be as effective as employing explicit psychological strategies (SEMA) in swaying human decision-making. By revealing the potential for covert AI influence, this study highlights a critical vulnerability in human-AI interactions, emphasizing the need for ethical safeguards and regulatory frameworks to ensure responsible deployment of AI technologies and protect human autonomy.

Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency

Coordinating multiple agents to collaboratively maximize submodular functions in unpredictable environments is a critical task with numerous applications in machine learning, robot planning and control. The existing approaches, such as the OSG algorithm, are often hindered by their poor approximation guarantees and the rigid requirement for a fully connected communication graph. To address these challenges, we firstly present a $\textbf{MA-OSMA}$ algorithm, which employs the multi-linear extension to transfer the discrete submodular maximization problem into a continuous optimization, thereby allowing us to reduce the strict dependence on a complete graph through consensus techniques. Moreover, $\textbf{MA-OSMA}$ leverages a novel surrogate gradient to avoid sub-optimal stationary points. To eliminate the computationally intensive projection operations in $\textbf{MA-OSMA}$, we also introduce a projection-free $\textbf{MA-OSEA}$ algorithm, which effectively utilizes the KL divergence by mixing a uniform distribution. Theoretically, we confirm that both algorithms achieve a regret bound of $\widetilde{O}(\sqrt{\frac{C_{T}T}{1-\beta}})$ against a $(\frac{1-e^{-c}}{c})$-approximation to the best comparator in hindsight, where $C_{T}$ is the deviation of maximizer sequence, $\beta$ is the spectral gap of the network and $c$ is the joint curvature of submodular objectives. This result significantly improves the $(\frac{1}{1+c})$-approximation provided by the state-of-the-art OSG algorithm. Finally, we demonstrate the effectiveness of our proposed algorithms through simulation-based multi-target tracking.

Two-stage memetic algorithm for blind equalization in direct-sequence/code-division multiple-access Systems

This paper proposes a novel memetic algorithm (MA) for the blind equalization of digital multiuser channels with Direct-Sequence / Code-Division Multiple-Access (DS/CDMA) sharing scheme. Equalization involves two different tasks, the estimation of: (1) channel response and (2) transmitted data. The corresponding channel model is first analyzed and then the MA is developed for this specific communication system. Convergence, population diversity and near-far resistance have been analyzed. Numerical experiments include comparative results with traditional multiuser detectors as well as with other nature-inspired approaches. Proposed receiver is proved to allow higher transmission rates over existing channels, while supporting stronger interferences as well as fading and time-variant effects. Required computation requisites are kept moderate in most cases. Proposed MA saves approximately 80% of computation time with respect to a standard genetic algorithm and about 15% with respect to a similar two-stage memetic algorithm, while keeping a statistically significant higher performance. Besides, complexity increases only by a factor of 5, when the number of active users doubles, instead of 32x found for the optimum maximum likelihood algorithm. The proposed method also exhibits high near-far resistance and achieves accurate channel response estimates, becoming an interesting and viable alternative to so far proposed methods.

Latency Minimization for Movable Antennas-Enabled Relay-aided D2D Mobile Edge Computing Communication Systems

Device-to-device (D2D)-assisted mobile edge computing (MEC) is one of the critical technologies of future sixth generation (6G) networks. The core of D2D-assisted MEC is to reduce system latency for network edge UEs by supporting cloud computing services, thereby achieving high-speed transmission. Due to the sensitivity of communication signals to obstacles, relaying is adopted to enhance the D2D-assisted MEC system's performance and its coverage area. However, relay nodes and the base station (BS) are typically equipped with large-scale antenna arrays. This increases the cost of relay-assisted D2D MEC systems and limits their deployment. Movable antenna (MA) technology is used to work around this limitation without compromising performance. Specifically, the core of MA technology lies in optimizing the antenna positions to increase system capacity. Therefore, this paper proposes a novel resource allocation scheme for MA-enhanced relay-assisted D2D MEC systems. Specifically, the MA positions and beamforming of user equipments (UEs), relay, and BS as well as the allocation of resources and the computation task offloading rate at the MEC server, all are optimized herein with the objective of minimizing the maximum latency while satisfying computation and communication rate constraints. Since this is a multivariable non-convex problem, a parallel and distributed penalty dual decomposition (PDD) based algorithm is developed and combined with successive convex approximation (SCA) to solve this non-convex problem. The results of extensive numerical analyses show that the proposed algorithm significantly improves the performance of the MA-enhanced relay-assisted D2D communication system compared to a counterpart where relays and the BS are equiped with traditional fixed-position antenna (FPA).

MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt

Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary image information from different modalities. Recently, large-scale pre-trained models like CLIP have demonstrated impressive performance in traditional single-modal object ReID tasks. However, they remain unexplored for multi-modal object ReID. Furthermore, current multi-modal aggregation methods have obvious limitations in dealing with long sequences from different modalities. To address above issues, we introduce a novel framework called MambaPro for multi-modal object ReID. To be specific, we first employ a Parallel Feed-Forward Adapter (PFA) for adapting CLIP to multi-modal object ReID. Then, we propose the Synergistic Residual Prompt (SRP) to guide the joint learning of multi-modal features. Finally, leveraging Mamba's superior scalability for long sequences, we introduce Mamba Aggregation (MA) to efficiently model interactions between different modalities. As a result, MambaPro could extract more robust features with lower complexity. Extensive experiments on three multi-modal object ReID benchmarks (i.e., RGBNT201, RGBNT100 and MSVR310) validate the effectiveness of our proposed methods. The source code is available at https://github.com/924973292/MambaPro.

MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution

Recent advances in image super-resolution (SR) have significantly benefited from the incorporation of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent drawbacks, especially the significantly increased computational demands. Moreover, the feature perception within a fixed-size window of existing models restricts the effective receptive fields and the intermediate feature diversity. This study demonstrates that a flexible integration of attention across diverse spatial extents can yield significant performance enhancements. In line with this insight, we introduce Multi-Range Attention Transformer (MAT) tailored for SR tasks. MAT leverages the computational advantages inherent in dilation operation, in conjunction with self-attention mechanism, to facilitate both multi-range attention (MA) and sparse multi-range attention (SMA), enabling efficient capture of both regional and sparse global features. Further coupled with local feature extraction, MAT adeptly capture dependencies across various spatial ranges, improving the diversity and efficacy of its feature representations. We also introduce the MSConvStar module, which augments the model's ability for multi-range representation learning. Comprehensive experiments show that our MAT exhibits superior performance to existing state-of-the-art SR models with remarkable efficiency (~3.3 faster than SRFormer-light).

Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing

With the growing scale and complexity of video data, efficiently processing long video sequences poses significant challenges due to the quadratic increase in memory and computational demands associated with existing transformer-based Large Multi-modal Models (LMMs). To address these issues, we introduce Video-Ma$^2$mba, a novel architecture that incorporates State Space Models (SSMs) within the Mamba-2 framework, replacing the attention mechanisms. This allows the LMMs to scale linearly in terms of time and memory requirements, making it feasible to handle long-duration video content. Furthermore, we enhance the memory efficiency introducing the Multi-Axis Gradient Checkpointing (MA-GC) method, which strategically manages memory by retaining only essential activations across multiple computational axes. Our approach significantly reduces the memory footprint compared to standard gradient checkpointing. Empirical analyses show that Video-Ma$^2$mba can process extensive video sequences-equivalent to millions of tokens or over two hours of continuous sequences at 1 FPS-on a single GPU. By maintaining a detailed capture of temporal dynamics, our model improves the accuracy and relevance of responses in long video understanding tasks, demonstrating substantial advantages over existing frameworks.

MaDiNet: Mamba Diffusion Network for SAR Target Detection

The fundamental challenge in SAR target detection lies in developing discriminative, efficient, and robust representations of target characteristics within intricate non-cooperative environments. However, accurate target detection is impeded by factors including the sparse distribution and discrete features of the targets, as well as complex background interference. In this study, we propose a \textbf{Ma}mba \textbf{Di}ffusion \textbf{Net}work (MaDiNet) for SAR target detection. Specifically, MaDiNet conceptualizes SAR target detection as the task of generating the position (center coordinates) and size (width and height) of the bounding boxes in the image space. Furthermore, we design a MambaSAR module to capture intricate spatial structural information of targets and enhance the capability of the model to differentiate between targets and complex backgrounds. The experimental results on extensive SAR target detection datasets achieve SOTA, proving the effectiveness of the proposed network. Code is available at \href{https://github.com/JoyeZLearning/MaDiNet}{https://github.com/JoyeZLearning/MaDiNet}.