Hong Peng

Chengwen Liu, Xiaomin Yu, Zhuoyue Chang et al.

In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative retrieval, and multi-hop reasoning-based verification. To bridge this gap, we construct the first video deep research benchmark, VideoDR. VideoDR centers on video-conditioned open-domain video question answering, requiring cross-frame visual anchor extraction, interactive web retrieval, and multi-hop reasoning over joint video-web evidence; through rigorous human annotation and quality control, we obtain high-quality video deep research samples spanning six semantic domains. We evaluate multiple closed-source and open-source multimodal large language models under both the Workflow and Agentic paradigms, and the results show that Agentic is not consistently superior to Workflow: its gains depend on a model's ability to maintain the initial video anchors over long retrieval chains. Further analysis indicates that goal drift and long-horizon consistency are the core bottlenecks. In sum, VideoDR provides a systematic benchmark for studying video agents in open-web settings and reveals the key challenges for next-generation video deep research agents.

Hong Peng, Chen Jiang, Jing Cheng et al.

Magnetic resonance imaging serves as an essential tool for clinical diagnosis. However, it suffers from a long acquisition time. The utilization of deep learning, especially the deep generative models, offers aggressive acceleration and better reconstruction in magnetic resonance imaging. Nevertheless, learning the data distribution as prior knowledge and reconstructing the image from limited data remains challenging. In this work, we propose a novel Hankel-k-space generative model (HKGM), which can generate samples from a training set of as little as one k-space data. At the prior learning stage, we first construct a large Hankel matrix from k-space data, then extract multiple structured k-space patches from the large Hankel matrix to capture the internal distribution among different patches. Extracting patches from a Hankel matrix enables the generative model to be learned from redundant and low-rank data space. At the iterative reconstruction stage, it is observed that the desired solution obeys the learned prior knowledge. The intermediate reconstruction solution is updated by taking it as the input of the generative model. The updated result is then alternatively operated by imposing low-rank penalty on its Hankel matrix and data consistency con-strain on the measurement data. Experimental results confirmed that the internal statistics of patches within a single k-space data carry enough information for learning a powerful generative model and provide state-of-the-art reconstruction.

Qiaoling Yang, Linkai Luo, Haoyu Zhang et al.

Support vector machine (SVM) and neural networks (NN) have strong complementarity. SVM focuses on the inner operation among samples while NN focuses on the operation among the features within samples. Thus, it is promising and attractive to combine SVM and NN, as it may provide a more powerful function than SVM or NN alone. However, current work on combining them lacks true integration. To address this, we propose a sample attention memory network (SAMN) that effectively combines SVM and NN by incorporating sample attention module, class prototypes, and memory block to NN. SVM can be viewed as a sample attention machine. It allows us to add a sample attention module to NN to implement the main function of SVM. Class prototypes are representatives of all classes, which can be viewed as alternatives to support vectors. The memory block is used for the storage and update of class prototypes. Class prototypes and memory block effectively reduce the computational cost of sample attention and make SAMN suitable for multi-classification tasks. Extensive experiments show that SAMN achieves better classification performance than single SVM or single NN with similar parameter sizes, as well as the previous best model for combining SVM and NN. The sample attention mechanism is a flexible module that can be easily deepened and incorporated into neural networks that require it.

Xiong Zhang, Hong Peng, Changlong Fu et al.

A significant number of anomalous nodes in the real world, such as fake news, noncompliant users, malicious transactions, and malicious posts, severely compromises the health of the graph data ecosystem and urgently requires effective identification and processing. With anomalies that span multiple data domains yet exhibit vast differences in features, cross-domain detection models face severe domain shift issues, which limit their generalizability across all domains. This study identifies and quantitatively analyzes a specific feature mismatch pattern exhibited by domain shift in graph anomaly detection, which we define as the \emph{Anomaly Disassortativity} issue ($\mathcal{AD}$). Based on the modeling of the issue $\mathcal{AD}$, we introduce a novel graph foundation model for anomaly detection. It achieves cross-domain generalization in different graphs, requiring only a single training phase to perform effectively across diverse domains. The experimental findings, based on fourteen diverse real-world graphs, confirm a breakthrough in the model's cross-domain adaptation, achieving a pioneering state-of-the-art (SOTA) level in terms of detection accuracy. In summary, the proposed theory of $\mathcal{AD}$ provides a novel theoretical perspective and a practical route for future research in generalist graph anomaly detection (GGAD). The code is available at https://anonymous.4open.science/r/Anonymization-TA-GGAD/.

Linkai Luo, Qiaoling Yang, Hong Peng et al.

The selection of Gaussian kernel parameters plays an important role in the applications of support vector classification (SVC). A commonly used method is the k-fold cross validation with grid search (CV), which is extremely time-consuming because it needs to train a large number of SVC models. In this paper, a new approach is proposed to train SVC and optimize the selection of Gaussian kernel parameters. We first formulate the training and the parameter selection of SVC as a minimax optimization problem named as MaxMin-L2-SVC-NCH, in which the minimization problem is an optimization problem of finding the closest points between two normal convex hulls (L2-SVC-NCH) while the maximization problem is an optimization problem of finding the optimal Gaussian kernel parameters. A lower time complexity can be expected in MaxMin-L2-SVC-NCH because CV is not needed. We then propose a projected gradient algorithm (PGA) for the training of L2-SVC-NCH. It is revealed that the famous sequential minimal optimization (SMO) algorithm is a special case of the PGA. Thus, the PGA can provide more flexibility than the SMO. Furthermore, the solution of the maximization problem is done by a gradient ascent algorithm with dynamic learning rate. The comparative experiments between MaxMin-L2-SVC-NCH and the previous best approaches on public datasets show that MaxMin-L2-SVC-NCH greatly reduces the number of models to be trained while maintaining competitive test accuracy. These findings indicate that MaxMin-L2-SVC-NCH is a better choice for SVC tasks.

Bo Yang, Hong Peng, Xiaohui Luo et al.

Breast cancer(BC) is a prevalent type of malignant tumor in women. Early diagnosis and treatment are vital for enhancing the patients' survival rate. Downsampling in deep networks may lead to loss of information, so for compensating the detail and edge information and allowing convolutional neural networks to pay more attention to seek the lesion region, we propose a multi-stages attention architecture based on NSNP neurons with autapses. First, unlike the single-scale attention acquisition methods of existing methods, we set up spatial attention acquisition at each feature map scale of the convolutional network to obtain an fusion global information on attention guidance. Then we introduce a new type of NSNP variants called NSNP neurons with autapses. Specifically, NSNP systems are modularized as feature encoders, recoding the features extracted from convolutional neural network as well as the fusion of attention information and preserve the key characteristic elements in feature maps. This ensures the retention of valuable data while gradually transforming high-dimensional complicated info into low-dimensional ones. The proposed method is evaluated on the public dataset BreakHis at various magnifications and classification tasks. It achieves a classification accuracy of 96.32% at all magnification cases, outperforming state-of-the-art methods. Ablation studies are also performed, verifying the proposed model's efficacy. The source code is available at XhuBobYoung/Breast-cancer-Classification.

Hao Ye, Jisheng Dang, Junfeng Fang et al.

Recent extensive research has demonstrated that the enhanced reasoning capabilities acquired by models through Reinforcement Learning with Verifiable Rewards (RLVR) are primarily concentrated within the rank-1 components. Predicated on this observation, we employed Periodic Rank-1 Substitution and identified a counterintuitive phenomenon: RLVR may exhibit implicit reward overfitting to the training dataset. Specifically, the model can achieve satisfactory performance on the test set even when its rewards remain relatively low during the training process. Furthermore, we characterize three distinct properties of RL training: (1) The effective rank-1 component in RLVR don't maintain other model knowledge except mathematical reasoning capability. (2) RLVR fundamentally functions by optimizing a specific singular spectrum. The distribution of singular values of almost all linear layers in RLVR-trained model behaves like heavy-tailed distribution. (3) the left singular vectors associated with rank-1 components demonstrate a stronger alignment tendency during training, which echoes the discovery that RLVR is optimizing sampling efficiency in essence. Taken together, our findings and analysis further reveal how RLVR shapes model parameters and offer potential insights for improving existing RL paradigms or other training paradigms to implement continual learning.

Xiong Zhang, Hong Peng, Zhenli He et al.

Anomalies often occur in real-world information networks/graphs, such as malevolent users, malicious comments, banned users, and fake news in social graphs. The latest graph anomaly detection methods use a novel mechanism called truncated affinity maximization (TAM) to detect anomaly nodes without using any label information and achieve impressive results. TAM maximizes the affinities among the normal nodes while truncating the affinities of the anomalous nodes to identify the anomalies. However, existing TAM-based methods truncate suspicious nodes according to a rigid threshold that ignores the specificity and high-order affinities of different nodes. This inevitably causes inefficient truncations from both normal and anomalous nodes, limiting the effectiveness of anomaly detection. To this end, this paper proposes a novel truncation model combining contextual and global affinity to truncate the anomalous nodes. The core idea of the work is to use contextual truncation to decrease the affinity of anomalous nodes, while global truncation increases the affinity of normal nodes. Extensive experiments on massive real-world datasets show that our method surpasses peer methods in most graph anomaly detection tasks. In highlights, compared with previous state-of-the-art methods, the proposed method has +15\% $\sim$ +20\% improvements in two famous real-world datasets, Amazon and YelpChi. Notably, our method works well in large datasets, Amazin-all and YelpChi-all, and achieves the best results, while most previous models cannot complete the tasks.

Bo Yang, Hong Peng, Chenggang Guo et al.

Prompt treatment for melanoma is crucial. To assist physicians in identifying lesion areas precisely in a quick manner, we propose a novel skin lesion segmentation technique namely SLP-Net, an ultra-lightweight segmentation network based on the spiking neural P(SNP) systems type mechanism. Most existing convolutional neural networks achieve high segmentation accuracy while neglecting the high hardware cost. SLP-Net, on the contrary, has a very small number of parameters and a high computation speed. We design a lightweight multi-scale feature extractor without the usual encoder-decoder structure. Rather than a decoder, a feature adaptation module is designed to replace it and implement multi-scale information decoding. Experiments at the ISIC2018 challenge demonstrate that the proposed model has the highest Acc and DSC among the state-of-the-art methods, while experiments on the PH2 dataset also demonstrate a favorable generalization ability. Finally, we compare the computational complexity as well as the computational speed of the models in experiments, where SLP-Net has the highest overall superiority

Yuxuan Nie, Yutong Song, Jinjie Yang et al.

Drug combinations are essential in cancer therapy, leveraging synergistic drug-drug interactions (DDI) to enhance efficacy and combat resistance. However, the vast combinatorial space makes experimental screening impractical, and existing computational models struggle to capture the complex, bidirectional nature of DDIs, often relying on independent drug encoding or simplistic fusion strategies that miss fine-grained inter-molecular dynamics. Moreover, state-of-the-art graph-based approaches suffer from high computational costs, limiting scalability for real-world drug discovery. To address this, we propose DPASyn, a novel drug synergy prediction framework featuring a dual-attention mechanism and Precision-Aware Quantization (PAQ). The dual-attention architecture jointly models intra-drug structures and inter-drug interactions via shared projections and cross-drug attention, enabling fine-grained, biologically plausible synergy modeling. While this enhanced expressiveness brings increased computational resource consumption, our proposed PAQ strategy complements it by dynamically optimizing numerical precision during training based on feature sensitivity-reducing memory usage by 40% and accelerating training threefold without sacrificing accuracy. With LayerNorm-stabilized residual connections for training stability, DPASyn outperforms seven state-of-the-art methods on the O'Neil dataset (13,243 combinations) and supports full-batch processing of up to 256 graphs on a single GPU, setting a new standard for efficient and expressive drug synergy prediction.

Jiahao Wang, Hong Peng, Shengchao Chen et al.

Retinal optical coherence tomography (OCT) images provide crucial insights into the health of the posterior ocular segment. Therefore, the advancement of automated image analysis methods is imperative to equip clinicians and researchers with quantitative data, thereby facilitating informed decision-making. The application of deep learning (DL)-based approaches has gained extensive traction for executing these analysis tasks, demonstrating remarkable performance compared to labor-intensive manual analyses. However, the acquisition of Retinal OCT images often presents challenges stemming from privacy concerns and the resource-intensive labeling procedures, which contradicts the prevailing notion that DL models necessitate substantial data volumes for achieving superior performance. Moreover, limitations in available computational resources constrain the progress of high-performance medical artificial intelligence, particularly in less developed regions and countries. This paper introduces a novel ensemble learning mechanism designed for recognizing retinal diseases under limited resources (e.g., data, computation). The mechanism leverages insights from multiple pre-trained models, facilitating the transfer and adaptation of their knowledge to Retinal OCT images. This approach establishes a robust model even when confronted with limited labeled data, eliminating the need for an extensive array of parameters, as required in learning from scratch. Comprehensive experimentation on real-world datasets demonstrates that the proposed approach can achieve superior performance in recognizing Retinal OCT images, even when dealing with exceedingly restricted labeled datasets. Furthermore, this method obviates the necessity of learning extensive-scale parameters, making it well-suited for deployment in low-resource scenarios.

Hanshu Cai, Yiwen Gao, Shuting Sun et al.

According to the World Health Organization, the number of mental disorder patients, especially depression patients, has grown rapidly and become a leading contributor to the global burden of disease. However, the present common practice of depression diagnosis is based on interviews and clinical scales carried out by doctors, which is not only labor-consuming but also time-consuming. One important reason is due to the lack of physiological indicators for mental disorders. With the rising of tools such as data mining and artificial intelligence, using physiological data to explore new possible physiological indicators of mental disorder and creating new applications for mental disorder diagnosis has become a new research hot topic. However, good quality physiological data for mental disorder patients are hard to acquire. We present a multi-modal open dataset for mental-disorder analysis. The dataset includes EEG and audio data from clinically depressed patients and matching normal controls. All our patients were carefully diagnosed and selected by professional psychiatrists in hospitals. The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications. The 128-electrodes EEG signals of 53 subjects were recorded as both in resting state and under stimulation; the 3-electrode EEG signals of 55 subjects were recorded in resting state; the audio data of 52 subjects were recorded during interviewing, reading, and picture description. We encourage other researchers in the field to use it for testing their methods of mental-disorder analysis.

Hong Peng, Yu Hu, Jiazhou Chen et al.

The performance of most the clustering methods hinges on the used pairwise affinity, which is usually denoted by a similarity matrix. However, the pairwise similarity is notoriously known for its vulnerability of noise contamination or the imbalance in samples or features, and thus hinders accurate clustering. To tackle this issue, we propose to use information among samples to boost the clustering performance. We proved that a simplified similarity for pairs, denoted by a fourth order tensor, equals to the Kronecker product of pairwise similarity matrices under decomposable assumption, or provide complementary information for which the pairwise similarity missed under indecomposable assumption. Then a high order similarity matrix is obtained from the tensor similarity via eigenvalue decomposition. The high order similarity capturing spatial information serves as a robust complement for the pairwise similarity. It is further integrated with the popular pairwise similarity, named by IPS2, to boost the clustering performance. Extensive experiments demonstrated that the proposed IPS2 significantly outperformed previous similarity-based methods on real-world datasets and it was capable of handling the clustering task over under-sampled and noisy datasets.