Search

An isolated attosecond vortex $\gamma$-ray pulse is generated by using a relativistic spatiotemporal optical vortex (STOV) laser in particle-in-cell simulations. A $\sim$ 300-attosecond electron slice with transverse orbital angular momentum (TOAM) is initially selected and accelerated by the central spatiotemporal singularity of the STOV laser. This slice then collides with the laser's reflected Gaussian-like front from a planar target, initiating nonlinear Compton scattering and resulting in an isolated, attosecond ($\sim$ 300 as), highly collimated ($\sim$ 4$\degree$), ultra-brilliant ($\sim 5\times 10^{24}$ photons/s/mm$^2$/mrad$^2$/0.1\%BW at 1 MeV) $\gamma$-ray pulse. This STOV-driven approach overcomes the significant beam divergence and complex two-laser requirements of prior Gaussian-based methods while introducting TOAM to the attosecond $\gamma$-ray pulse, which opens avenues for ultrafast imaging, nuclear excitation, and detection applications.

A new on-chip light source configuration has been proposed, which utilizes the interaction between microwave and a dielectric nanopillar array to generate a periodic electromagnetic near field, and applies periodic transverse acceleration to relativistic electrons to generate high-energy photon radiation. Here the dielectric nanopillar array interacting with microwave acts as the electron undulator, in which the near field drives electrons to oscillate. When an electron beam operates in this nanopillar array in this light source configuration, it is subjected to a periodic transverse near-field force, and will radiate X-ray or even gamma-ray high energy photons after a relativistic frequency up-conversion. Compared with the laser-dielectric undulator based on the interaction between strong lasers and nanostructures to generate a plasmonic near field, this configuration is less prone to damage during operation.

Multi-modal image fusion aims to combine information from different modes to create a single image with comprehensive information and detailed textures. However, fusion models based on convolutional neural networks encounter limitations in capturing global image features due to their focus on local convolution operations. Transformer-based models, while excelling in global feature modeling, confront computational challenges stemming from their quadratic complexity. Recently, the Selective Structured State Space Model has exhibited significant potential for long-range dependency modeling with linear complexity, offering a promising avenue to address the aforementioned dilemma. In this paper, we propose FusionMamba, a novel dynamic feature enhancement method for multimodal image fusion with Mamba. Specifically, we devise an improved efficient Mamba model for image fusion, integrating efficient visual state space model with dynamic convolution and channel attention. This refined model not only upholds the performance of Mamba and global modeling capability but also diminishes channel redundancy while enhancing local enhancement capability. Additionally, we devise a dynamic feature fusion module (DFFM) comprising two dynamic feature enhancement modules (DFEM) and a cross modality fusion mamba module (CMFM). The former serves for dynamic texture enhancement and dynamic difference perception, whereas the latter enhances correlation features between modes and suppresses redundant intermodal information. FusionMamba has yielded state-of-the-art (SOTA) performance across various multimodal medical image fusion tasks (CT-MRI, PET-MRI, SPECT-MRI), infrared and visible image fusion task (IR-VIS) and multimodal biomedical image fusion dataset (GFP-PC), which is proved that our model has generalization ability. The code for FusionMamba is available at https://github.com/millieXie/FusionMamba.

This paper focuses on the challenge of answering questions in scenarios that are composed of rich and complex dynamic audio-visual components. Although existing Multimodal Large Language Models (MLLMs) can respond to audio-visual content, these responses are sometimes ambiguous and fail to describe specific audio-visual events. To overcome this limitation, we introduce the CAT, which enhances MLLM in three ways: 1) besides straightforwardly bridging audio and video, we design a clue aggregator that aggregates question-related clues in dynamic audio-visual scenarios to enrich the detailed knowledge required for large language models. 2) CAT is trained on a mixed multimodal dataset, allowing direct application in audio-visual scenarios. Notably, we collect an audio-visual joint instruction dataset named AVinstruct, to further enhance the capacity of CAT to model cross-semantic correlations. 3) we propose AI-assisted ambiguity-aware direct preference optimization, a strategy specialized in retraining the model to favor the non-ambiguity response and improve the ability to localize specific audio-visual objects. Extensive experimental results demonstrate that CAT outperforms existing methods on multimodal tasks, especially in Audio-Visual Question Answering (AVQA) tasks. The codes and the collected instructions are released at https://github.com/rikeilong/Bay-CAT.

This paper investigates the unsourced random access (URA) problem with a massive multiple-input multiple-output receiver that serves wireless devices in the near-field of radiation. We employ an uncoupled transmission protocol without appending redundancies to the slot-wise encoded messages. To exploit the channel sparsity for block length reduction while facing the collapsed sparse structure in the angular domain of near-field channels, we propose a sparse channel sampling method that divides the angle-distance (polar) domain based on the maximum permissible coherence. Decoding starts with retrieving active codewords and channels from each slot. We address the issue by leveraging the structured channel sparsity in the spatial and polar domains and propose a novel turbo-based recovery algorithm. Furthermore, we investigate an off-grid compressed sensing method to refine discretely estimated channel parameters over the continuum that improves the detection performance. Afterward, without the assistance of redundancies, we recouple the separated messages according to the similarity of the users' channel information and propose a modified K-medoids method to handle the constraints and collisions involved in channel clustering. Simulations reveal that via exploiting the channel sparsity, the proposed URA scheme achieves high spectral efficiency and surpasses existing multi-slot-based schemes. Moreover, with more measurements provided by the overcomplete channel sampling, the near-field-suited scheme outperforms its counterpart of the far-field., Comment: Accepted by IEEE Transactions on Communications

This paper investigates the unsourced random access (URA) scheme to accommodate numerous machine-type users communicating to a base station equipped with multiple antennas. Existing works adopt a slotted transmission strategy to reduce system complexity; they operate under the framework of coupled compressed sensing (CCS) which concatenates an outer tree code to an inner compressed sensing code for slot-wise message stitching. We suggest that by exploiting the MIMO channel information in the angular domain, redundancies required by the tree encoder/decoder in CCS can be removed to improve spectral efficiency, thereby an uncoupled transmission protocol is devised. To perform activity detection and channel estimation, we propose an expectation-maximization-aided generalized approximate message passing algorithm with a Markov random field support structure, which captures the inherent clustered sparsity structure of the angular domain channel. Then, message reconstruction in the form of a clustering decoder is performed by recognizing slot-distributed channels of each active user based on similarity. We put forward the slot-balanced K-means algorithm as the kernel of the clustering decoder, resolving constraints and collisions specific to the application scene. Extensive simulations reveal that the proposed scheme achieves a better error performance at high spectral efficiency compared to the CCS-based URA schemes., Comment: Accepted for publication in IEEE TCOM

Multi-task regression attempts to exploit the task similarity in order to achieve knowledge transfer across related tasks for performance improvement. The application of Gaussian process (GP) in this scenario yields the non-parametric yet informative Bayesian multi-task regression paradigm. Multi-task GP (MTGP) provides not only the prediction mean but also the associated prediction variance to quantify uncertainty, thus gaining popularity in various scenarios. The linear model of coregionalization (LMC) is a well-known MTGP paradigm which exploits the dependency of tasks through linear combination of several independent and diverse GPs. The LMC however suffers from high model complexity and limited model capability when handling complicated multi-task cases. To this end, we develop the neural embedding of coregionalization that transforms the latent GPs into a high-dimensional latent space to induce rich yet diverse behaviors. Furthermore, we use advanced variational inference as well as sparse approximation to devise a tight and compact evidence lower bound (ELBO) for higher quality of scalable model inference. Extensive numerical experiments have been conducted to verify the higher prediction quality and better generalization of our model, named NSVLMC, on various real-world multi-task datasets and the cross-fluid modeling of unsteady fluidized bed., Comment: 29 pages, 9 figures, 4 tables, preprint under review

This paper investigates the massive random access for a huge amount of user devices served by a base station (BS) equipped with a massive number of antennas. We consider a grant-free unsourced random access (U-RA) scheme where all users possess the same codebook and the BS aims at declaring a list of transmitted codewords and recovering the messages sent by active users. Most of the existing works concentrate on applying U-RA in the oversimplified independent and identically distributed (i.i.d.) channels. In this paper, we consider a fairly general joint-correlated MIMO channel model with line-of-sight components for the realistic outdoor wireless propagation environments. We conduct the activity detection for the emitted codewords by performing an improved coordinate descent approach with Bayesian learning automaton to solve a covariance-based maximum likelihood estimation problem. The proposed algorithm exhibits a faster convergence rate than traditional descent approaches. We further employ a coupled coding scheme to resolve the issue that the dimensions of the common codebook expand exponentially with user payload size in the practical massive machine-type communications scenario. Our simulations reveal that to achieve an error probability of 0.05 for reliable communications in correlated channels, one must pay a 0.9 to 1.3 dB penalty comparing to the minimum signal to noise ratio needed in i.i.d. channels on condition that a sufficient number of receiving antennas is equipped at the BS., Comment: accepted by Globecom 2020