Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framework for commercial ads that fuses Chain-of-Thought reasoning with rule-based policy principles and a critic-guided reward. A rule-driven ICoT data-synthesis pipeline jump-starts training by generating structured scene descriptions, reasoning chains and labels, cutting annotation costs. Reinforcement learning then refines the model using a composite reward balancing causal coherence with policy adherence. A multitask architecture models intra-modal manipulations (e.g., exaggerated imagery) and cross-modal mismatches (e.g., subtitle–speech drift), boosting robustness. Experiments on real short-video ads show BLM-Guard surpasses strong baselines in accuracy, consistency and generalization.

Precise alignment of the micropipette tip is crucial for robotic cell micromanipulation, enabling delicate procedures such as cell transfer, rotation, and immobilization. However, due to the limited field of view and depth perception under high-magnification microscopy, it poses significant challenges in accurately identifying misalignment and effectively controlling micropipette motion for adjustment. This paper comprehensively analyzes and addresses the misalignment problem, particularly that caused by the improper inclination angle of the micropipette holder. A vision-guided robotic control strategy for automatic micropipette alignment is integrated into a 5-degree-of-freedom (5-DOF) micromanipulator, enabling autonomous detection, adjustment, and positioning of the micropipette. The proposed method ensures precise trajectory tracking and compensates for geometric uncertainties introduced by fabrication or installation errors. Experimental validation demonstrates that the proposed system achieved a mean absolute error below 3 µm for positioning the tip of the micropipette at the focal plane during the procedure of adjustment. Meanwhile, the robotic method required significantly less time to stably rotate the micropipette compared to manual operation for cell manipulation. The vertical alignment error was less than 3 µm along a 250 µm micropipette tip segment. These results confirm that the proposed approach significantly enhances speed, accuracy, and repeatability in micropipette-based micro-manipulation, providing a robust solution for high-throughput biological experiments and clinical applications.

The protein-ligand affinity prediction task aims to predict the binding strength of small molecule ligands to specific proteins, which is crucial in the fields of drug design and molecular biology, and can accelerate the drug discovery. The structure complementarity between protein and ligand plays a critical role in determining binding strength , but most of current deep learning-based affinity prediction models usually extracted the features of protein and ligand by these two detached modules. which limits the exchange of information for capturing interactions and struggles to capture proteins’ important residues. To address these limitations. we introduce CIP. which takes the combination of GNN, Conditional Updating and Proximity Embedding for the first time. Compared to existing models, CIP has several significant advantages. First, Conditional updating modifies the ligand’s local features based on the protein’s global features, and vice versa , enhancing structural complementarity to capture intricate interactions. Second, encoding the relative distances between proximal residue-atom pairs highlights critical residues. Additionally, our model integrates covalent and noncovalent interactions to obtain more comprehensive graph representations. Experiments on the PDB-bind 2016 benchmark demonstrate that CIP outperforms the original method with improvements of 2.3%, 3.2%, 2.8%, 3.8%, and 3.2% across five baselines. Furthermore, visualization results reveal that CIP effectively captures intricate interactions and crucial residues.The implemented code and dataset are available online at https://github.com/xfcui/CIP.

Information on burned areas (BAs) is particularly important for research on forest fires. Mapping BAs contributes to managing and preventing further destruction. BA mapping has long been constrained by the temporal and spatial resolution of satellite data and classification accuracy, while also neglecting the spectral characteristics of optical satellites. To address this issue, a novel method for mapping and extracting BAs using a semantic segmentation model has been proposed herein. Leveraging medium spatial resolution satellites, Landsat-8 and Sentinel-2, and after determining the optimal spectral band combination, a spectral-spatial module was integrated into the U-Net; this resulted in a new model, known as the SSU-Net. SSU-Net precisely extracted BAs from a single post-fire image. The optimal band combinations for Landsat-8 and Sentinel-2 were bands 7-5-4 and 12-8-4, respectively. SSU-Net achieved an$F1$score of 0.9296 and an intersection over union (IoU) of 0.8707 on Landsat-8 data. It achieved slightly higher performance on Sentinel-2 with an$F1$score of 0.9314 and IoU of 0.8752. Compared with U-Net, SSU-Net improved the$F1$scores by 4.8% and 3.4% for Landsat-8 and Sentinel-2, respectively, and IoU by 7.7% and 5.9%. In terms of generalization, SSU-Net achieved an$F1$score of 0.9151 when trained on Landsat-8 data and tested on Sentinel-2 data, and 0.9313 vice versa, with improvements of 2.1% and 5.1% over U-Net, respectively. SSU-Net also demonstrated higher accuracy and generalization in BA mapping, supporting the integration of multisource remote sensing data and emphasizing its crucial role in sustainable forest management on a global scale.

Computational aesthetics evaluation has made great achievements in the field of visual arts, but the research work on music still needs to be explored. Although the existing work of music generation is very substantial, the quality of music score generated by AI is relatively poor compared with that created by human composers. The music scores created by AI are usually monotonous and devoid of emotion. Based on Birkhoff’s aesthetic measure, this paper proposes an objective quantitative evaluation method for homophony music score aesthetic quality assessment. The main contributions of our work are as follows: first, we put forward a homophony music score aesthetic model to objectively evaluate the quality of music score as a baseline model; second, we put forward eight basic music features and four music aesthetic features.

The current multiple-input multiple-output (MIMO) systems are still mainly implemented based on the centralized architecture, which thus has to process a huge amount of base-band data. In particular, the central processing unit (CPU) needs a large bus bandwidth to accommodate the prohibitive baseband data transmission, which hinders effective system implementation, especially for the massive MIMO systems. Moreover, the centralized scheme lacks flexibility and scalability when facing varying sizes of antenna arrays and diverse applications. This paper proposes an efficient decentralized bidirectional-chain (DBC) equalizer architecture. The advantages of the DBC architecture are two-fold. First, it can reduce the data traffic transmitted from the antennas to the processing unit by categorizing them into clusters, each of which is equipped with a local processing unit (LPU). Second, it can reduce the time delay by updating all clusters in parallel. To sufficiently exploit the proposed DBC architecture, we further propose efficient parallel iterative algorithms. The DBC-based parallelizable iterative algorithms achieve the state-of-the-art performance in terms of convergence rate and bit error rate. Finally, simulation results are provided to confirm the effectiveness and superiority of our proposal.

In the tasks of image aesthetic quality assessment, it is difficult to reach both the high score area and low score area due to the normal distribution of aesthetic datasets. To reduce the error in labelling and solve the problem of normal data distribution, we propose a new aesthetic mixed dataset with classification and regression called AMD-CR, and we train a meta reweighting network to reweight the loss of training data differently. In addition, we provide a training strategy according to different stages based on pseudo labels, and then we use it for aesthetic training according to different stages in classification and regression tasks. In the construction of the network structure, we construct an aesthetic adaptive block (AAB) structure that can adapt to any size of the input images. Besides, we also use the efficient channel attention (ECA) to strengthen the feature extracting ability of each task. The experimental result shows that our method improves 0.1112 compared with the conventional method in SROCC. The method can also help to find best aesthetic path planning for unmanned aerial vehicles (UAV) and vehicles.

With the continuous development of social software and multimedia technology, images have become a kind of important carrier for spreading information and socializing. How to evaluate an image comprehensively has become the focus of recent researches. The traditional image aesthetic assessment methods often adopt single numerical overall assessment scores, which has certain subjectivity and can no longer meet the higher aesthetic requirements. In this article, we construct an new image attribute dataset called aesthetic mixed dataset with attributes (AMD-A) and design external attribute features for fusion. Besides, we propose an efficient method for image aesthetic attribute assessment on mixed multi-attribute dataset and construct a multitasking network architecture by using the EfficientNet-B0 as the backbone network. Our model can achieve aesthetic classification, overall scoring, and attribute scoring. In each sub-network, we improve the feature extraction through ECA channel attention module. As for the final overall scoring, we adopt the idea of the teacher-student network and use the classification sub-network to guide the aesthetic overall fine-grain regression. Experimental results, using the MindSpore, show that our proposed method can effectively improve the performance of the aesthetic overall and attribute assessment.

Cell manipulation is a critical procedure in related biological applications such as embryo biopsy and intracytoplasmic sperm injection (ICSI), where the biological cell is required to be oriented to the desired position. To bridge the gap between the techniques and the clinical applications, a robotic micromanipulation method, which utilizes friction forces to rotate the cell with standard micropipettes, is presented in this paper. Force models for both in-plane and out-of-plane rotations are well established and analyzed for the rotation control. For better controllability, calibration steps are also designed for adjusting the orientation of the micropipette with a more efficient way. A cell orientation recognition algorithm based on the superpixel segmentation and spectral clustering is reported and achieved high validation accuracy (96%) for estimating the orientation of the oocyte. The extracted visual information further facilitates the feedback control of cell rotation. Experimental results show that the overall success rate for the cell rotation control was about 95% with orientation precision of ±1°.

We propose a new method for bistatic scattering from hybrid subsurface profiles with multilayer rough interfaces and flat boundaries, which the fast method is firstly demonstrated by strictly theoretical formulas in the framework of classical small perturbation method (SPM) without other else approximation and assumption strategy. What is more, we can obtain general compact closed-form first-order perturbation solutions of hybrid subsurface profiles with an arbitrary number of rough and smooth interfaces, which is necessary to insure a successful inversion process. We employ improved inverse algorithms and get successful inverse process based on the proposed forward model.

A physics model for the electromagnetic scattering from large-scale rough surface of layered medium is established. Stratton-Chu integral equation and Kirchhoff approximation are adopted to calculate the electromagnetic scattering field. The Gaussian random rough surface is selected to simulate the actual rough surface of layered medium. The scattering echo is detected with a single-station nadir-looking radar sounder. A comparison of radar echoes from Martian mare areas with different roughness is demonstrated. A radar sounder echo simulator is developed, which could be used to validate the radar echoes processing and to support the interpretation of Martian exploration data. By using the simulator, the B-scan images of Martian highland areas with different crater density are studied. Besides, special attentions are paid to the effect of radar waveforms on the B-scan imaging of highland areas. Simulation-based results show that the method presented is feasible in the detection of Martian subsurface structure.

This paper proposes a novel phase-shift migration (PSM) based algorithm in the Through-the-wall (TWI) imaging. Unlike the current methods, our technique uses the Green's function to compensate the multiple reflections between the wall and the free space. This compensation can be carried out as the preprocessing for the traditional PSM. Simulation results using synthetic-generated data show that the proposed method can well enhance the imaging results in the TWI imaging.

A two-dimensional Multi-Resolution Time-Domain iterative formula based on the basis function of compactly supported wavelet is derived, and a basis function selectable electromagnetic scattering forward model is established according to the derived formula. By calculating the electromagnetic fields of target scattering object, the simulation results show that the proposed model has the advantages of high computing accuracy and speed, and requires few number of grids compared with the conventional FDTD algorithm.