ABSTRACT Underwater images harbor abundant resources for marine science and applications. The fusion of Transformers and CNNs has emerged as a promising approach for salient object detection. These encoders extract hierarchical features at different scales, each exhibiting unique characteristics. Low‐level features primarily focus on detailed information, whereas deep features encapsulate higher level semantic information. Motivated by these observations, we design a hierarchical fusion network combining the Swin Transformer with a CNN for underwater salient object detection. Underwater images are preprocessed via an enhancement algorithm utilised to restore attenuated spectral characteristics. At the low‐level encoder stages, global features derived from the Swin Transformer and local features extracted from ResNet50 are integrated via an adaptive interactive fusion strategy, which prioritises detail preservation. At the high‐level encoder stages, long‐range dependency features are aggregated with local features via a cross‐attention fusion module, which emphasises semantic interaction. An upsampling and fusion decoder is designed to generate a coarse saliency map, densely integrating the hierarchical features while preserving fine details. Finally, a post‐refinement network is utilised to further enhance detection performance by leveraging boundary and contextual information, achieving an accurate salient object segmentation result. Experimental results demonstrate that our method achieves F ‐measure scores of 0.9322, 0.9247, and 0.8332 on the USOD10K, USOD, and UFO‐120 datasets, highlighting the efficacy of hierarchical fusion of Swin Transformer and CNN for underwater salient object detection. The code of our method is available at https://github.com/leckie711/hfusod .

Predicting unknown transcription factor-target gene (TF-target gene) interactions based on gene regulatory networks (GRNs) is critical for understanding cellular functions and biological discovery. Existing computational methods focus on the statistic corelation and neglect the semantic information of biomedical knowledge. To address this, we propose BioLinkGPT, a novel framework that integrates the robust textual comprehension capabilities of Large Language Models (LLMs) with graph neural networks (GNNs) to capture structural information of GRN. BioLinkGPT leverages gene information and the known TF-target gene relationships from literature to predict unknown TF-target gene interactions and improve its performance via a two-stage instruction fine-tuning strategy. We construct a comprehensive GRN dataset focused on human infectious diseases, and experimental results show that BioLinkGPT significantly outperforms existing baselines in link prediction metrics. We validate the model's accurate identification of known regulatory relationships and find that BioLinkGPT successfully uncover potential regulatory interactions with high confidence and biological relevance. BioLinkGPT offers an efficient and precise computational tool to infer TF-target gene interactions, accelerating research on infectious disease mechanisms and drug target development.

Zero-Shot Industrial Anomaly Detection (ZSIAD) aims to identify and localize anomalies in industrial images from unseen categories. Owing to the powerful generalization capabilities, Vision-Language Models (VLMs) have achieved growing interest in ZSIAD. To guide the model toward understanding and localizing the semantically complex industrial anomalies, existing VLM-based methods have attempted to provide additional prompts to the model through learnable text prompt templates. However, these zero-shot methods lack detailed descriptions of specific anomalies, making it difficult to classify and segment the diverse range of industrial anomalies accurately. To address the aforementioned issue, we firstly propose the multi-stage prompt generation agent for ZSIAD. Specifically, we leverage the Multi-modal Language Large Model (MLLM) to articulate the detailed differential information between normal and test samples, which can provide detailed text prompts to the model through further refinement and anti-false alarm constraint. Moreover, we introduce the Visual Fundamental Model (VFM) to generate anomaly-related attention prompts for more accurate localization of anomalies with varying sizes and shapes. Extensive experiments on seven real-world industrial anomaly detection datasets have shown that the proposed method not only outperforms recent SOTA methods, but also its explainable prompts provide the model with a more intuitive basis for anomaly identification.

Efforts in weakly-supervised video anomaly detection center on detecting abnormal events within videos by coarse-grained labels, which has been successfully applied to many real-world applications. However, a significant limitation of most existing methods is that they are only effective for specific objects in specific scenarios, which makes them prone to misclassification or omission when confronted with previously unseen anomalies. Relative to conventional anomaly detection tasks, Open-world Weakly-supervised Video Anomaly Detection (OWVAD) poses greater challenges due to the absence of labels and fine-grained annotations for unknown anomalies. To address the above problem, we propose a multi-scale evidential vision-language model to achieve open-world video anomaly detection. Specifically, we leverage generalized visual-language associations derived from CLIP to harness the full potential of large pre-trained models in addressing the OWVAD task. Subsequently, we integrate a multi-scale temporal modeling module with a multimodal evidence collector to achieve precise frame-level detection of both seen and unseen anomalies. Extensive experiments on two widely-utilized benchmarks have conclusively validated the effectiveness of our method. The code will be made publicly available.

Computing-in-memory (CIM) shows its superiority in lots of applications like neural network inference. Recently, there are lots of exploration of the application of Magnetic Random-Access Memory (MRAM) in CIM. This paper aims to investigate the potential of Spin-Orbit-Torque-MRAM (SOT-MRAM) in CIM and proposes a high area and energy efficiency SOT-MRAM CIM macro based on a 6T-4J weight group. The bit-cell array adopts series-parallel hybrid architecture, which combines both serial and parallel configurations of Magnetic Tunnel Junction (MTJ) to solve the problem of high energy cost and low flexibility caused by MRAM-series and MRAM-parallel architecture, respectively. Additionally, the proposed SOT-MRAM CIM macro incorporates a multi-method modulation scheme, ranging from input unit to array, which meanwhile allows for configurable input precision (2/4/6/8-bit). The SOT-MRAM CIM macro is designed and verified in both 180nm and 28nm nodes, based on the verified electrical performance of the SOT-MRAM array in a 200-nm wafer pre-fabricated. The simulation results in 28nm show that this macro can achieve energy efficiency of 23.7~29.6 Tops/W at 8-bit input and output precision.

Recently, Adder Neural Networks (AdderNets) have gained widespread attention as an alternative to traditional Convolutional Neural Networks (CNNs) for deep learning tasks. AdderNets use lightweight addition operations to replace multiplication and accumulation (MAC) operations, but can keep almost the same accuracy compared to other CNNs. Nevertheless, challenges still exist with regards to hardware resources, power consumption, and communication bandwidth, primarily due to the ‘Von-Neumann bottlenecks’. However, computing-in-memory (CIM) architecture based on magnetic random-access memory (MRAM) has great potential for edge DNN implementation. In this paper, we propose a novel CIM paradigm using a novel Toggle-Spin-Torques (TST) driven MRAM for energy-efficient AdderNets (called CiTST_AdderNets). In CiTST_AdderNets, MRAM is driven by the interplay of the field-free spin orbit torque (SOT) effect and the spin transfer torque (STT) effect, which offers a fascinating prospect for energy efficiency and speed. Furthermore, a novel CIM paradigm is proposed to implement the dominating subtraction and sum operations in AdderNets, reducing data transfer and the related energy. Meanwhile, a highly parallel array structure integrating computation and storage is designed to support CiTST_AdderNets. In addition, a mapping strategy is proposed to efficiently map the convolution layer on the array. Fully connected layers can also be efficiently computed. The CiTST-AdderNets macro is designed by using a 65-nm CMOS process. Results show that our CiTST-AdderNets consumes about 1.65 mJ, 9.29 mJ, and 42.46 mJ for running VGG8, ResNet-50, and ResNet-18 respectively at 8-bit fixed-point precision. Compared to state-of-the-art platforms, our macro achieves an energy efficiency improvement of 1.45 x to 66.78 x.

The popularization and application of 5G technology is about to open the era of global "data explosion". The traditional cloud computing model shows insufficient service support for resource-sensitive applications, especially in terms of latency, and edge computing can solve this problem by providing service support close to the user request side. This article formalizes the single application service deployment problem (SASDP) using the E-CARGO (Environment-Class, Agent, Role, Group, and Object) model. Through group role assignment (GRA), a high-satisfaction service deployment scheme for single application service deployment is designed, and satisfaction evaluation is established through delay to provide providers with satisfactory deployment solutions and achieve economic benefits. Finally, large-scale simulation experiments are carried out based on Python PuLP platform, and experiments show that our method is better than the baseline method in terms of overall satisfaction, user coverage and economy.

With the frequent occurrence of disasters, such as war, storms, hurricanes, and earthquakes, post-disaster rescue is particularly important. Based on the principle of life first life detection and rescue have become the primary task of post-disaster rescue. In this paper, the E-CARGO (Environments – Classes, Agents, Roles, Groups, and Objects) model is used to formalize the life detection and rescue problem. With the help of the idea of the convex hull algorithm, a Hierarchical Coverage Based on Square Algorithm (HCBS) is proposed to achieve the maximum coverage of the rescue area with the minimum number of detection areas, and then a rapid assignment of UAV life detection and rescue with minimized rescue cost is realized through group role assignment (GRA). Using the PuLP extension library of Python, we implement the proposed algorithm. The experiments show that the proposed method is fast and effective.