Guisong Liu

Qiugang Zhan, Ran Tao, Xiurui Xie et al.

In recent years, studies on image generation models of spiking neural networks (SNNs) have gained the attention of many researchers. Variational autoencoders (VAEs), as one of the most popular image generation models, have attracted a lot of work exploring their SNN implementation. Due to the constrained binary representation in SNNs, existing SNN VAE methods implicitly construct the latent space by an elaborated autoregressive network and use the network outputs as the sampling variables. However, this unspecified implicit representation of the latent space will increase the difficulty of generating high-quality images and introduces additional network parameters. In this paper, we propose an efficient spiking variational autoencoder (ESVAE) that constructs an interpretable latent space distribution and design a reparameterizable spiking sampling method. Specifically, we construct the prior and posterior of the latent space as a Poisson distribution using the firing rate of the spiking neurons. Subsequently, we propose a reparameterizable Poisson spiking sampling method, which is free from the additional network. Comprehensive experiments have been conducted, and the experimental results show that the proposed ESVAE outperforms previous SNN VAE methods in reconstructed & generated images quality. In addition, experiments demonstrate that ESVAE's encoder is able to retain the original image information more efficiently, and the decoder is more robust. The source code is available at https://github.com/QgZhan/ESVAE.

Guisong Liu, Xin Gao, Martin Dresler et al.

Automatic sleep staging commonly adopts Transformers under the assumption that they learn complex long-range dependencies. We challenge this view by revealing a neglected property of sleep sequences: strong local temporal continuity. We show that a randomly initialized Transformer, without any training, substantially improves sleep staging performance and consistently outperforms heuristic smoothing. We formalize this effect via a Random Attention Prior Kernel (RAPK), showing that random self-attention acts as an adaptive smoother by balancing global averaging and content-based similarity while preserving stage transitions. Using two metrics, the Local Smoothness Influence Index (LSII) and the Weighted Transition Entropy (WTE), we provide evidence that most performance gains in Transformer-based sleep staging arise from architectural inductive bias rather than parameter learning. Our results suggest that sleep staging can be effectively addressed with structure-driven smoothing mechanisms rather than complex dependency modeling, enabling more efficient and edge-deployable healthcare systems for large-scale physiological monitoring.

Guisong Liu, Pengfei Wei, Jainsong Zhang et al.

Mobile sleep staging serves as a foundational infrastructure for in-home sleep monitoring and closed-loop modulation. But existing sequential models such as RNNs and Transformers are computationally expensive for mobile deployment. In this paper, we propose Random Attention (RA), a lightweight temporal modeling module based on fixed random projections, which replaces learnable sequence modeling with similarity-based aggregation. RA introduces little additional parameters beyond the epoch encoder while enabling effective temporal smoothing. We further provide a theoretical interpretation via the Random Attention Prior Kernel (RAPK), which decomposes RA into a global smoothing term and a feature similarity term, offering an interpretable view of temporal sleep structure. Experiments on Sleep-EDF-20 and Sleep-EDF-78 show that RA consistently improves epoch-wise baselines by 1-3\% in accuracy and F1 score, while achieving competitive performance compared with LSTM, GRU, and Transformer models. RA also demonstrates strong generalization across different backbone encoders and improved robustness over conventional temporal smoothing methods. These results indicate that efficient sleep staging can be achieved through lightweight similarity-based temporal aggregation, making RA suitable for real-time wearable applications.

Qi Xue, Minrui Jiang, Runjia Zhang et al.

Existing methods for evaluating the harmfulness of content generated by large language models (LLMs) have been well studied. However, approaches tailored to multimodal large language models (MLLMs) remain underdeveloped and lack depth. This work highlights the crucial role of visual information in moderating content in visual question answering (VQA), a dimension often overlooked in current research. To bridge this gap, we introduce Falcon, a large-scale vision-language safety dataset containing 57,515 VQA pairs across 13 harm categories. The dataset provides explicit annotations for harmful attributes across images, instructions, and responses, thereby facilitating a comprehensive evaluation of the content generated by MLLMs. In addition, it includes the relevant harm categories along with explanations supporting the corresponding judgments. We further propose FalconEye, a specialized evaluator fine-tuned from Qwen2.5-VL-7B using the Falcon dataset. Experimental results demonstrate that FalconEye reliably identifies harmful content in complex and safety-critical multimodal dialogue scenarios. It outperforms all other baselines in overall accuracy across our proposed Falcon-test dataset and two widely-used benchmarks-VLGuard and Beavertail-V, underscoring its potential as a practical safety auditing tool for MLLMs.

Qiugang Zhan, Jinbo Cao, Xiurui Xie et al.

Spiking federated learning is an emerging distributed learning paradigm that allows resource-constrained devices to train collaboratively at low power consumption without exchanging local data. It takes advantage of both the privacy computation property in federated learning (FL) and the energy efficiency in spiking neural networks (SNN). Thus, it is highly promising to revolutionize the efficient processing of multimedia data. However, existing spiking federated learning methods employ a random selection approach for client aggregation, assuming unbiased client participation. This neglect of statistical heterogeneity affects the convergence and accuracy of the global model significantly. In our work, we propose a credit assignment-based active client selection strategy, the SFedCA, to judiciously aggregate clients that contribute to the global sample distribution balance. Specifically, the client credits are assigned by the firing intensity state before and after local model training, which reflects the local data distribution difference from the global model. Comprehensive experiments are conducted on various non-identical and independent distribution (non-IID) scenarios. The experimental results demonstrate that the SFedCA outperforms the existing state-of-the-art spiking federated learning methods, and requires fewer communication rounds.

Guisong Liu, Wenjie Deng, Xiurui Xie et al.

As the third-generation neural networks, Spiking Neural Networks (SNNs) have great potential on neuromorphic hardware because of their high energy-efficiency. However, Deep Spiking Reinforcement Learning (DSRL), i.e., the Reinforcement Learning (RL) based on SNNs, is still in its preliminary stage due to the binary output and the non-differentiable property of the spiking function. To address these issues, we propose a Deep Spiking Q-Network (DSQN) in this paper. Specifically, we propose a directly-trained deep spiking reinforcement learning architecture based on the Leaky Integrate-and-Fire (LIF) neurons and Deep Q-Network (DQN). Then, we adapt a direct spiking learning algorithm for the Deep Spiking Q-Network. We further demonstrate the advantages of using LIF neurons in DSQN theoretically. Comprehensive experiments have been conducted on 17 top-performing Atari games to compare our method with the state-of-the-art conversion method. The experimental results demonstrate the superiority of our method in terms of performance, stability, robustness and energy-efficiency. To the best of our knowledge, our work is the first one to achieve state-of-the-art performance on multiple Atari games with the directly-trained SNN.

Jean-Paul Ainam, Ke Qin, Guisong Liu

In this paper, we present an attention mechanism scheme to improve person re-identification task. Inspired by biology, we propose Self Attention Grid (SAG) to discover the most informative parts from a high-resolution image using its internal representation. In particular, given an input image, the proposed model is fed with two copies of the same image and consists of two branches. The upper branch processes the high-resolution image and learns high dimensional feature representation while the lower branch processes the low-resolution image and learn a filtering attention grid. We apply a max filter operation to non-overlapping sub-regions on the high feature representation before element-wise multiplied with the output of the second branch. The feature maps of the second branch are subsequently weighted to reflect the importance of each patch of the grid using a softmax operation. Our attention module helps the network learn the most discriminative visual features of multiple image regions and is specifically optimized to attend feature representation at different levels. Extensive experiments on three large-scale datasets show that our self-attention mechanism significantly improves the baseline model and outperforms various state-of-art models by a large margin.

Jean-Paul Ainam, Ke Qin, Guisong Liu et al.

Person re-identification (re-id) is a cross-camera retrieval task which establishes a correspondence between images of a person from multiple cameras. Deep Learning methods have been successfully applied to this problem and have achieved impressive results. However, these methods require a large amount of labeled training data. Currently labeled datasets in person re-id are limited in their scale and manual acquisition of such large-scale datasets from surveillance cameras is a tedious and labor-intensive task. In this paper, we propose a framework that performs intelligent data augmentation and assigns partial smoothing label to generated data. Our approach first exploits the clustering property of existing person re-id datasets to create groups of similar objects that model cross-view variations. Each group is then used to generate realistic images through adversarial training. Our aim is to emphasize feature similarity between generated samples and the original samples. Finally, we assign a non-uniform label distribution to the generated samples and define a regularized loss function for training. The proposed approach tackles two problems (1) how to efficiently use the generated data and (2) how to address the over-smoothness problem found in current regularization methods. Extensive experiments on four larges cale datasets show that our regularization method significantly improves the Re-ID accuracy compared to existing methods.