The surrogate gradient (SG) method has shown significant promise in enhancing the performance of deep spiking neural networks (SNNs), but it also introduces vulnerabilities to adversarial attacks. Although spike coding strategies and neural dynamics parameters have been extensively studied for their impact on robustness, the critical role of gradient magnitude, which reflects the model's sensitivity to input perturbations, remains underexplored. In SNNs, the gradient magnitude is primarily determined by the interaction between the membrane potential distribution (MPD) and the SG function. In this study, we investigate the relationship between the MPD and SG and their implications for improving the robustness of SNNs. Our theoretical analysis reveals that reducing the proportion of membrane potentials lying within the gradient-available range of the SG function effectively mitigates the sensitivity of SNNs to input perturbations. Building upon this insight, we propose a novel MPD-driven surrogate gradient regularization (MPD-SGR) method, which enhances robustness by explicitly regularizing the MPD based on its interaction with the SG function. Extensive experiments across multiple image classification benchmarks and diverse network architectures confirm that the MPD-SGR method significantly enhances the resilience of SNNs to adversarial perturbations and exhibits strong generalizability across diverse network configurations, SG functions, and spike encoding schemes.

Compound fault diagnosis in multi-joint industrial robots is a critical yet underexplored problem in industrial internet of things, where the simultaneous degradation of multiple joints poses a severe challenge for reliable operation. Unlike conventional methods limited to single-fault scenarios, this paper addresses the compositional generalization challenge—requiring models trained only on simple faults to accurately recognize unseen higher-order fault compositions. To this end, we propose StateMix Network (SMNet), a multi-stage architecture that preserves atomic joint-level representations before compositional diagnosis. Specifically, a Single-Joint Feature Extraction (SJFE) backbone extracts clean joint-private features, which are then fused by an Attention-Guided Dilated Fusion (AGDF) neck employing parallel Cascaded Dilated Convolution Blocks (CDCBs) bracketed by a dual-path attention mechanism for scale- and context-aware integration. Finally, a Mamba-based sequence mixer models long-range cross-joint dependencies to capture global fault dynamics. Extensive experiments on in-situ vibration data from a single six-joint industrial robot platform, under a strict train-on-simple/evaluate-on-complex protocol, demonstrate that SMNet consistently outperforms representative baselines in macro-Precision, Recall, and F1-score, particularly on unseen triple- and quadruple-joint compositions. Ablation and sensitivity analyses further validate the effectiveness of each module. This work presents a diagnostic approach that effectively generalizes from simple to complex fault scenarios in industrial robots.

We propose Diff-Shadow, a global-guided diffusion model for high-quality shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover images with obvious boundaries. In contrast, diffusion-based methods can generate better content but they are not exempt from issues related to inconsistent illumination. In this work, we combine the advantages of diffusion models and global guidance to realize shadow-free restoration. Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images. A Reweight Cross Attention (RCA) module is designed to integrate global contextual information of non-shadow regions into the local branch. We further design a Global-guided Sampling Strategy (GSS) that mitigates patch boundary issues and ensures consistent illumination across shaded and unshaded regions in the recovered image. Comprehensive experiments on three publicly standard datasets ISTD, ISTD+, and SRD have demonstrated the effectiveness of Diff-Shadow. Compared to state-of-the-art methods, our method achieves a significant improvement in terms of PSNR, increasing from 32.33dB to 33.69dB on the ISTD dataset.

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges. By encoding camera settings into a time-aware camera-conditioned affine modulation (TCCAM), RNSD generates more realistic noise distributions under various camera conditions. Additionally, RNSD integrates a multi-scale content-aware module (MCAM), enabling the generation of structured noise with spatial correlations across multiple frequencies. We also introduce Deep Image Prior Sampling (DIPS), a learnable sampling sequence based on depth image prior, which significantly accelerates the sampling process while maintaining the high quality of synthesized noise. Extensive experiments demonstrate that our RNSD method significantly outperforms existing techniques in synthesizing realistic noise under multiple metrics and improving image denoising performance.

Spiking Neural Networks (SNNs), also referred to as the third generation of artificial neural networks, are highly prized for their biological realism, robustness, and low power requirements. SNNs are crucial in fields such as object detection, image recognition, etc. The classification of short text plays an significant role in the development of chatbots and intent detection. It is also an important task that is widely used in many downstream tasks. However, studies applying SNNs to short text classification are limited. This paper provides a new model that uses SNNs to classify short texts. SNNs are difficult to train directly when using deep models and cannot employ large-scale language models to learn good embeddings. To resolve the challenge, we apply the character-level encoding method and convert analog neural networks into SNNs. To begin with, we represent character-level text using a temporal-and-rate joint horizontal encoding method. Then we develop a tailored deep Convolutional Neural Network (CNN) model for classifying texts. At the inference stage, we convert the tailored CNN model into an SNN model. To test the effectiveness of the proposed method, we conduct text encoding experiments on the NAMES dataset and short text classification experiments on both the 20-newsgroups dataset and the emoji-mult dataset. Experiments demonstrate that the proposed method can obtain classification accuracies that are better than or comparable to other methods.

In text-based message exchange services, non-verbal expressions, such as emoticons, are typically used. However, their usage is intuitive, and many questions persist as to how emoticons affect the emotional aspect of messages. Therefore, we formulate the effect of emoticons on emotions of tweets with an emoticon and propose a method for computing emotion values of tweets with an emoticon. Initially, emotion values of emoticons and those of tweets with an emoticon are determined based on results of questionnaires. Subsequently, emotion values of tweets are calculated via two sentiment analysis tools. We then apply multiple regression analysis to the three types of emotion values, and thus we obtain multiple regression equations to compute emotion values of tweets with an emoticon. Our performance evaluation indicates that the proposed method is effective in terms of computing values of the following nine emotions: "Sorrow," "Disgust," "Relief," "Fear," "Liking," "Joy," "Surprise," "Anger," and "Shame."