Bo Gao

Miao Wang, Yuling Shi, Yijiang Li et al.

Text-based role-playing models can imitate character styles, yet they often fail to reflect a scene's atmosphere and evolving tension, both essential for immersive applications such as Virtual Reality (VR) games and interactive narratives. We study video-grounded role-playing dialogue and introduce EBM-RL (Eye-Brain-Mouth Reinforcement Learning), a decoupled GRPO-based framework that explicitly separates observation ([perception]), reasoning ([think]), and utterance ([answer]). This structure promotes human-like sensory grounding by compelling the model to first attend to visual cues, then form internal interpretations, and finally generate context-appropriate dialogue. EBM-RL integrates four complementary rewards: (i) CLIP-based scene-text alignment to improve ambiance and emotion; (ii) a Perceptual-Cognitive reward that encourages [perception] and [think] processes that increase the likelihood of the reference response; (iii) answer accuracy to ensure faithfulness; and (iv) a dense format reward to enforce the desired structured output. Extensive experiments demonstrate that EBM-RL substantially outperforms text-only role-playing baselines and larger-scale vision-language models on our immersive role-playing benchmark, delivering simultaneous gains in visual-atmosphere consistency and character authenticity. Beyond the role-playing domain, EBM-RL also exhibits strong zero-shot generalization: without any additional fine-tuning, it consistently improves performance on out-of-domain VideoQA benchmarks. We additionally release an open-source dataset for video-grounded role-playing dialogue.

Zhiyuan Wu, Sheng Sun, Yuwei Wang et al.

The growing interest in intelligent services and privacy protection for mobile devices has given rise to the widespread application of federated learning in Multi-access Edge Computing (MEC). Diverse user behaviors call for personalized services with heterogeneous Machine Learning (ML) models on different devices. Federated Multi-task Learning (FMTL) is proposed to train related but personalized ML models for different devices, whereas previous works suffer from excessive communication overhead during training and neglect the model heterogeneity among devices in MEC. Introducing knowledge distillation into FMTL can simultaneously enable efficient communication and model heterogeneity among clients, whereas existing methods rely on a public dataset, which is impractical in reality. To tackle this dilemma, Federated MultI-task Distillation for Multi-access Edge CompuTing (FedICT) is proposed. FedICT direct local-global knowledge aloof during bi-directional distillation processes between clients and the server, aiming to enable multi-task clients while alleviating client drift derived from divergent optimization directions of client-side local models. Specifically, FedICT includes Federated Prior Knowledge Distillation (FPKD) and Local Knowledge Adjustment (LKA). FPKD is proposed to reinforce the clients' fitting of local data by introducing prior knowledge of local data distributions. Moreover, LKA is proposed to correct the distillation loss of the server, making the transferred local knowledge better match the generalized representation. Experiments on three datasets show that FedICT significantly outperforms all compared benchmarks in various data heterogeneous and model architecture settings, achieving improved accuracy with less than 1.2% training communication overhead compared with FedAvg and no more than 75% training communication round compared with FedGKT.

Bo Gao, Chang Liu, Yuyang Miao et al.

Recent advancements in Large Generative Models (LGMs) have revolutionized multi-modal generation. However, generating illustrated storybooks remains an open challenge, where prior works mainly decompose this task into separate stages, and thus, holistic multi-modal grounding remains limited. Besides, while safety alignment is studied for text- or image-only generation, existing works rarely integrate child-specific safety constraints into narrative planning and sequence-level multi-modal verification. To address these limitations, we propose BookAgent, a safety-aware multi-agent collaboration framework designed for high-quality, safety-aware visual narratives. Different from prior story visualization models that assume a fixed storyline sequence, BookAgent targets end-to-end storybook synthesis from a user draft by jointly planning, scripting, illustrating, and globally repairing inconsistencies. To ensure precise multi-modal grounding, BookAgent dynamically calibrates page-level alignment between textual scripts and visual layouts. Furthermore, BookAgent calibrates holistic consistency from the temporal dimension, by verifying-then-rectifying global inconsistencies in character identity and storytelling logic. Extensive experiments demonstrate that BookAgent significantly outperforms current methods in narrative coherence, visual consistency, and safety compliance, offering a robust paradigm for reliable agents in complex multi-modal creation. The implementation will be publicly released at https://github.com/bogao-code/BookAgent/tree/main.

Qingxiang Liu, Sheng Sun, Min Liu et al.

Traffic flow forecasting (TFF) is of great importance to the construction of Intelligent Transportation Systems (ITS). To mitigate communication burden and tackle with the problem of privacy leakage aroused by centralized forecasting methods, Federated Learning (FL) has been applied to TFF. However, existing FL-based approaches employ batch learning manner, which makes the pre-trained models inapplicable to subsequent traffic data, thus exhibiting subpar prediction performance. In this paper, we perform the first study of forecasting traffic flow adopting Online Learning (OL) manner in FL framework and then propose a novel prediction method named Online Spatio-Temporal Correlation-based Federated Learning (FedOSTC), aiming to guarantee performance gains regardless of traffic fluctuation. Specifically, clients employ Gated Recurrent Unit (GRU)-based encoders to obtain the internal temporal patterns inside traffic data sequences. Then, the central server evaluates spatial correlation among clients via Graph Attention Network (GAT), catering to the dynamic changes of spatial closeness caused by traffic fluctuation. Furthermore, to improve the generalization of the global model for upcoming traffic data, a period-aware aggregation mechanism is proposed to aggregate the local models which are optimized using Online Gradient Descent (OGD) algorithm at clients. We perform comprehensive experiments on two real-world datasets to validate the efficiency and effectiveness of our proposed method and the numerical results demonstrate the superiority of FedOSTC.

Cong Yang, Bipin Indurkhya, John See et al.

Skeleton Ground Truth (GT) is critical to the success of supervised skeleton extraction methods, especially with the popularity of deep learning techniques. Furthermore, we see skeleton GTs used not only for training skeleton detectors with Convolutional Neural Networks (CNN) but also for evaluating skeleton-related pruning and matching algorithms. However, most existing shape and image datasets suffer from the lack of skeleton GT and inconsistency of GT standards. As a result, it is difficult to evaluate and reproduce CNN-based skeleton detectors and algorithms on a fair basis. In this paper, we present a heuristic strategy for object skeleton GT extraction in binary shapes and natural images. Our strategy is built on an extended theory of diagnosticity hypothesis, which enables encoding human-in-the-loop GT extraction based on clues from the target's context, simplicity, and completeness. Using this strategy, we developed a tool, SkeView, to generate skeleton GT of 17 existing shape and image datasets. The GTs are then structurally evaluated with representative methods to build viable baselines for fair comparisons. Experiments demonstrate that GTs generated by our strategy yield promising quality with respect to standard consistency, and also provide a balance between simplicity and completeness.

Zhiyuan Wu, Sheng Sun, Yuwei Wang et al.

The increasing demand for intelligent services and privacy protection of mobile and Internet of Things (IoT) devices motivates the wide application of Federated Edge Learning (FEL), in which devices collaboratively train on-device Machine Learning (ML) models without sharing their private data. Limited by device hardware, diverse user behaviors and network infrastructure, the algorithm design of FEL faces challenges related to resources, personalization and network environments. Fortunately, Knowledge Distillation (KD) has been leveraged as an important technique to tackle the above challenges in FEL. In this paper, we investigate the works that KD applies to FEL, discuss the limitations and open problems of existing KD-based FEL approaches, and provide guidance for their real deployment.

Yuwei Wang, Runhan Li, Hao Tan et al.

Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. Data heterogeneity is a critical challenge in realistic FL settings, as it causes significant performance deterioration due to discrepancies in optimization among local models. In this work, we focus on label distribution skew, a common scenario in data heterogeneity, where the data label categories are imbalanced on each client. To address this issue, we propose FedBalance, which corrects the optimization bias among local models by calibrating their logits. Specifically, we introduce an extra private weak learner on the client side, which forms an ensemble model with the local model. By fusing the logits of the two models, the private weak learner can capture the variance of different data, regardless of their category. Therefore, the optimization direction of local models can be improved by increasing the penalty for misclassifying minority classes and reducing the attention to majority classes, resulting in a better global model. Extensive experiments show that our method can gain 13\% higher average accuracy compared with state-of-the-art methods.

Yuhan Tang, Aoxu Zhang, Zhiyuan Wu et al.

Federated Distillation (FD) offers an innovative approach to distributed machine learning, leveraging knowledge distillation for efficient and flexible cross-device knowledge transfer without necessitating the upload of extensive model parameters to a central server. While FD has gained popularity, its vulnerability to poisoning attacks remains underexplored. To address this gap, we previously introduced FDLA (Federated Distillation Logits Attack), a method that manipulates logits communication to mislead and degrade the performance of client models. However, the impact of FDLA on participants with different identities and the effects of malicious modifications at various stages of knowledge transfer remain unexplored. To this end, we present PCFDLA (Peak-Controlled Federated Distillation Logits Attack), an advanced and more stealthy logits poisoning attack method for FD. PCFDLA enhances the effectiveness of FDLA by carefully controlling the peak values of logits to create highly misleading yet inconspicuous modifications. Furthermore, we introduce a novel metric for better evaluating attack efficacy, demonstrating that PCFDLA maintains stealth while being significantly more disruptive to victim models compared to its predecessors. Experimental results across various datasets confirm the superior impact of PCFDLA on model accuracy, solidifying its potential threat in federated distillation systems.

Wei Sun, Bo Gao, Ke Xiong et al.

In federated learning (FL), although the original intention of available but not visible data is to allay data privacy concerns, it potentially brings new security threats, particularly poisoning attacks that target such not visible local data. Intuitively, such data poisoning attacks have great potential in stealthily degrading global FL outcomes, and are expected to be even stealthier if being enhanced by generative models like generative adversarial networks (GANs). However, existing defense methods have not been thoroughly challenged in this regard and generally fail to be aware of a local generation of seemingly legitimate poisoned data. With a growing concern on potentially stealthier attacks, in this paper, a cost-effective defense mechanism named Model Consistency-Based Defense (MCD) is proposed, which offers a comprehensive examination of available local models across multiple feature dimensions, providing an indirect yet effective means of identifying hidden data poisoning attackers. To push the limit of MCD against stealthier attacks, we propose a new GAN-based data poisoning attack model named VagueGAN and an unsupervised variant of it, which can be flexibly deployed to generate seemingly legitimate but noisy poisoned data. The consistency of GAN outputs revealed by VagueGAN helps strengthen MCD to work against stealthier GAN-based attacks as well as other mainstream ones. Extensive experiments on multiple open datasets (MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100, and Mini-Imagenet) indicate that our attack method better balances the trade-off between attack effectiveness and stealthiness with low complexity. More importantly, our defense mechanism is shown to be more competent in identifying a variety of poisoned data, particularly stealthier GAN-poisoned ones.

Bo Gao, Yuan Wang, Qingsong Wei et al.

Decentralized finance (DeFi) applications depend on accurate price oracles to ensure secure transactions, yet these oracles are highly vulnerable to manipulation, enabling attackers to exploit smart contract vulnerabilities for unfair asset valuation and financial gain. Detecting such manipulations traditionally relies on the manual effort of experienced experts, presenting significant challenges. In this paper, we propose a novel LLM-driven framework that automates the detection of price oracle manipulations by leveraging the complementary strengths of different LLM models (LLMs). Our approach begins with domain-specific knowledge extraction, where an LLM model synthesizes precise insights about price oracle vulnerabilities from top-tier academic papers, eliminating the need for profound expertise from developers or auditors. This knowledge forms the foundation for a second LLM model to generate structured, context-aware chain of thought prompts, which guide a third LLM model in accurately identifying manipulation patterns in smart contracts. We validate the effectiveness of framework through experiments on 60 known vulnerabilities from 46 real-world DeFi attacks or projects spanning 2021 to 2023. The best performing combination of LLMs (Haiku-Haiku-4o-mini) identified by AiRacleX demonstrate a 2.58-times improvement in recall (0.667 vs 0.259) compared to the state-of-the-art tool GPTScan, while maintaining comparable precision. Furthermore, our framework demonstrates the feasibility of replacing commercial models with open-source alternatives, enhancing privacy and security for developers.

Wei Sun, Yijun Chen, Bo Gao et al.

Federated learning (FL) is vulnerable to data poisoning attacks due to its distributed nature. Although recent GAN-based data poisoning methods have indicated the potential of using generative AI to generate seemingly legitimate poisoned data, the inherent consistency of GAN outputs can still reveal a sign of data poisoning. In this paper, we propose a diffusion-based data poisoning framework against FL systems, which leverages a Poisoning-Oriented Conditional Diffusion Model (PCDM) to enable fine-grained control over the local generation of poisoned data while ensuring both attack effectiveness and stealthiness. Our PCDM incorporates an adjustable poisoning vector within the global context to precisely control the generation of poisoned data, with theoretical guarantees on attack performance. Furthermore, it employs a novel jumping diffusion strategy for lightweight and efficient poisoned data generation. We conduct the most systematic and broad experimental evaluation for FL poisoning attacks against various defenses, including advanced Byzantine robust aggregation mechanisms, on four open datasets: MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100, and a real-world wireless-specific dataset VRAI. Our results demonstrate that PCDM is less likely to exhibit statistical anomalies compared with the state-of-the-art methods while more effectively degrading global FL performance, which poses a significant risk to data security in FL.

Siyuan Ma, Bo Gao, Zikai Xiao et al.

Recent test-time reasoning methods improve performance by generating more candidate chains or searching over larger reasoning trees, but they typically lack explicit control over when to expand, what to prune, how to repair, and when to abstain. We introduce CoT2-Meta, a training-free metacognitive reasoning framework that combines object-level chain-of-thought generation with meta-level control over partial reasoning trajectories. The framework integrates four components: strategy-conditioned thought generation, tree-structured search, an online process oracle for step-level reasoning evaluation, and a meta-controller that allocates computation through expansion, pruning, repair, stopping, and fallback decisions. Under matched inference budgets, CoT2-Meta consistently outperforms strong single-path, sampling-based, and search-based baselines, including ReST-MCTS. On the default backbone, it achieves 92.8 EM on MATH, 90.4 accuracy on GPQA, 98.65 EM on GSM8K, 75.8 accuracy on BBEH, 85.6 accuracy on MMMU-Pro, and 48.8 accuracy on HLE, with gains over the strongest non-CoT2-Meta baseline of +3.6, +5.2, +1.15, +2.0, +4.3, and +4.3 points, respectively. Beyond these core results, the framework remains effective across a broader 15-benchmark suite spanning knowledge and QA, multi-hop reasoning, coding, and out-of-distribution evaluation. Additional analyses show better compute scaling, improved calibration, stronger selective prediction, targeted repair behavior, and consistent gains across backbone families. These results suggest that explicit metacognitive control is a practical design principle for reliable and compute-efficient test-time reasoning systems.

Xingsheng Chen, Xianpei Mu, Deyu Yi et al.

Multivariate time series forecasting is fundamental to numerous domains such as energy, finance, and environmental monitoring, where complex temporal dependencies and cross-variable interactions pose enduring challenges. Existing Transformer-based methods capture temporal correlations through attention mechanisms but suffer from quadratic computational cost, while state-space models like Mamba achieve efficient long-context modeling yet lack explicit temporal pattern recognition. Therefore we introduce UniMamba, a unified spatial-temporal forecasting framework that integrates efficient state-space dynamics with attention-based dependency learning. UniMamba employs a Mamba Variate-Channel Encoding Layer enhanced with FFT-Laplace Transform and TCN to capture global temporal dependencies, and a Spatial Temporal Attention Layer to jointly model inter-variate correlations and temporal evolution. A Feedforward Temporal Dynamics Layer further fuses continuous and discrete contexts for accurate forecasting. Comprehensive experiments on eight public benchmark datasets demonstrate that UniMamba consistently outperforms state-of-the-art forecasting models in both forecasting accuracy and computational efficiency, establishing a scalable and robust solution for long-sequence multivariate time-series prediction.

Xingsheng Chen, Regina Zhang, Bo Gao et al.

Time series prediction plays a pivotal role across diverse domains such as finance, healthcare, energy systems, and environmental modeling. However, existing approaches often struggle to balance efficiency, scalability, and accuracy, particularly when handling long-range dependencies and irregularly sampled data. To address these challenges, we propose MODE, a unified framework that integrates Low-Rank Neural Ordinary Differential Equations (Neural ODEs) with an Enhanced Mamba architecture. As illustrated in our framework, the input sequence is first transformed by a Linear Tokenization Layer and then processed through multiple Mamba Encoder blocks, each equipped with an Enhanced Mamba Layer that employs Causal Convolution, SiLU activation, and a Low-Rank Neural ODE enhancement to efficiently capture temporal dynamics. This low-rank formulation reduces computational overhead while maintaining expressive power. Furthermore, a segmented selective scanning mechanism, inspired by pseudo-ODE dynamics, adaptively focuses on salient subsequences to improve scalability and long-range sequence modeling. Extensive experiments on benchmark datasets demonstrate that MODE surpasses existing baselines in both predictive accuracy and computational efficiency. Overall, our contributions include: (1) a unified and efficient architecture for long-term time series modeling, (2) integration of Mamba's selective scanning with low-rank Neural ODEs for enhanced temporal representation, and (3) substantial improvements in efficiency and scalability enabled by low-rank approximation and dynamic selective scanning.

Chenyang Li, Jieyuan Liu, Bin Li et al.

Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to understand environments and directly output actions. However, by default, VLA models may overly attend to image tokens in the task-irrelevant region, which we describe as 'distracting tokens'. This behavior can disturb the model from the generation of the desired action tokens in each step, affecting the success rate of tasks. In this paper, we introduce a simple yet effective plug-and-play Distracting Token Pruning (DTP) framework, which dynamically detects and prunes these distracting image tokens. By correcting the model's visual attention patterns, we aim to improve the task success rate, as well as exploring the performance upper boundaries of the model without altering its original architecture or adding additional inputs. Experiments on the SIMPLER Benchmark (Li et al., 2024) show that our method consistently achieving relative improvements in task success rates across different types of novel VLA models, demonstrating generalizability to transformer-based VLAs. Further analysis reveals a negative correlation between the task success rate and the amount of attentions in the task-irrelevant region for all models tested, highlighting a common phenomenon of VLA models that could guide future research. We also publish our code at: https://anonymous.4open.science/r/CBD3.

Jiaxun Yang, Yifei Han, Long Zhang et al.

Chinese Patronizing and Condescending Language (CPCL) is an implicitly discriminatory toxic speech targeting vulnerable groups on Chinese video platforms. The existing dataset lacks user comments, which are a direct reflection of video content. This undermines the model's understanding of video content and results in the failure to detect some CPLC videos. To make up for this loss, this research reconstructs a new dataset PCLMMPLUS that includes 103k comment entries and expands the dataset size. We also propose the CPCLDetector model with alignment selection and knowledge-enhanced comment content modules. Extensive experiments show the proposed CPCLDetector outperforms the SOTA on PCLMM and achieves higher performance on PCLMMPLUS . CPLC videos are detected more accurately, supporting content governance and protecting vulnerable groups. Code and dataset are available at https://github.com/jiaxunyang256/PCLD.

Shenwei Kang, Xin Zhang, Wen Liu et al.

Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal conveyed by facial expressions, speech, gestures, and behavioral cues over time. In this work we introduce DA-Mamba, a dialogue-aware multimodal architecture that replaces attention-heavy dialogue encoders with Mamba-based selective state-space processing to achieve linear time and memory complexity while retaining expressive cross-modal reasoning. We design a Mamba dialogue-aware selective state-space model composed of three core modules: a Dialogue-Aware Encoder, and two Mamba-based fusion mechanisms: Modality-Group Fusion and Partner-Group Fusion, these modules achieve expressive dialogue understanding. Extensive experiments on three standard benchmarks (NoXi, NoXi-Add, and MPIIGI) show that DA-Mamba surpasses prior state-of-the-art (SOTA) methods in concordance correlation coefficient (CCC), while reducing training time and peak memory; these gains enable processing much longer sequences and facilitate real-time deployment in resource-constrained, multi-party conversational settings. The source code will be available at: https://github.com/kksssssss-ssda/MMEA.

Ning Xu, Bo Gao, Hui Dou

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks. However, they remain exposed to jailbreak attacks, eliciting harmful responses. The nested scenario strategy has been increasingly adopted across various methods, demonstrating immense potential. Nevertheless, these methods are easily detectable due to their prominent malicious intentions. In this work, we are the first to find and systematically verify that LLMs' alignment defenses are not sensitive to nested scenarios, where these scenarios are highly semantically relevant to the queries and incorporate targeted toxic knowledge. This is a crucial yet insufficiently explored direction. Based on this, we propose RTS-Attack (Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge), an adaptive and automated framework to examine LLMs' alignment. By building scenarios highly relevant to the queries and integrating targeted toxic knowledge, RTS-Attack bypasses the alignment defenses of LLMs. Moreover, the jailbreak prompts generated by RTS-Attack are free from harmful queries, leading to outstanding concealment. Extensive experiments demonstrate that RTS-Attack exhibits superior performance in both efficiency and universality compared to the baselines across diverse advanced LLMs, including GPT-4o, Llama3-70b, and Gemini-pro. Our complete code is available at https://github.com/nercode/Work. WARNING: THIS PAPER CONTAINS POTENTIALLY HARMFUL CONTENT.

Zhangyi Hu, Jiemin Wu, Hua Xu et al.

Irregular Multivariate Time Series (IMTS) forecasting is challenging due to the unaligned nature of multi-channel signals and the prevalence of extensive missing data. Existing methods struggle to capture reliable temporal patterns from such data due to significant missing values. While pre-trained foundation models show potential for addressing these challenges, they are typically designed for Regularly Sampled Time Series (RTS). Motivated by the visual Mask AutoEncoder's (MAE) powerful capability for modeling sparse multi-channel information and its success in RTS forecasting, we propose VIMTS, a framework adapting Visual MAE for IMTS forecasting. To mitigate the effect of missing values, VIMTS first processes IMTS along the timeline into feature patches at equal intervals. These patches are then complemented using learned cross-channel dependencies. Then it leverages visual MAE's capability in handling sparse multichannel data for patch reconstruction, followed by a coarse-to-fine technique to generate precise predictions from focused contexts. In addition, we integrate self-supervised learning for improved IMTS modeling by adapting the visual MAE to IMTS data. Extensive experiments demonstrate VIMTS's superior performance and few-shot capability, advancing the application of visual foundation models in more general time series tasks. Our code is available at https://github.com/WHU-HZY/VIMTS.

Bo Gao, M. W. Spratling

Finding a template in a search image is an important task underlying many computer vision applications. Recent approaches perform template matching in a deep feature-space, produced by a convolutional neural network (CNN), which is found to provide more tolerance to changes in appearance. In this article we investigate if enhancing the CNN's encoding of shape information can produce more distinguishable features that improve the performance of template matching. This investigation results in a new template matching method that produces state-of-the-art results on a standard benchmark. To confirm these results we also create a new benchmark and show that the proposed method also outperforms existing techniques on this new dataset. Our code and dataset is available at: https://github.com/iminfine/Deep-DIM.

Bo Gao, Jingcheng Tong, Xingsheng Chen et al.

Detecting small objects in UAV remote sensing images and identifying surface defects in industrial inspection remain difficult tasks. These applications face common obstacles: features are sparse and weak, backgrounds are cluttered, and object scales vary dramatically. Current transformer-based detectors, while powerful, struggle with three critical issues. First, features degrade severely as networks downsample progressively. Second, spatial convolutions cannot capture long-range dependencies effectively. Third, standard upsampling methods inflate feature maps unnecessarily. We introduce DFIR-DETR to tackle these problems through dynamic feature aggregation combined with frequency-domain processing. Our architecture builds on three novel components. The DCFA module uses dynamic K-sparse attention, cutting complexity from O(N2) down to O(NK), and employs spatial gated linear units for better nonlinear modeling. The DFPN module applies amplitude-normalized upsampling to prevent feature inflation and uses dual-path shuffle convolution to retain spatial details across scales. The FIRC3 module operates in the frequency domain, achieving global receptive fields without sacrificing efficiency. We tested our method extensively on NEU-DET and VisDrone datasets. Results show mAP50 scores of 92.9% and 51.6% respectively-both state-of-the-art. The model stays lightweight with just 11.7M parameters and 41.2 GFLOPs. Strong performance across two very different domains confirms that DFIR-DETR generalizes well and works effectively in resource-limited settings for cross-scene small object detection.

Zhiyuan Wu, Tianliu He, Sheng Sun et al.

Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature of real-world data, particularly its tendency to grow in volume and diversify in classes over time. This oversight results in FL methods suffering from catastrophic forgetting, where the trained models inadvertently discard previously learned information upon assimilating new data. In response to this challenge, we propose a novel Federated Class-Incremental Learning (FCIL) method, named \underline{Fed}erated \underline{C}lass-Incremental \underline{L}earning with New-Class \underline{A}ugmented \underline{S}elf-Di\underline{S}tillation (FedCLASS). The core of FedCLASS is to enrich the class scores of historical models with new class scores predicted by current models and utilize the combined knowledge for self-distillation, enabling a more sufficient and precise knowledge transfer from historical models to current models. Theoretical analyses demonstrate that FedCLASS stands on reliable foundations, considering scores of old classes predicted by historical models as conditional probabilities in the absence of new classes, and the scores of new classes predicted by current models as the conditional probabilities of class scores derived from historical models. Empirical experiments demonstrate the superiority of FedCLASS over four baseline algorithms in reducing average forgetting rate and boosting global accuracy.

Quyang Pan, Sheng Sun, Zhiyuan Wu et al.

Federated Edge Learning (FEL) has emerged as a promising approach for enabling edge devices to collaboratively train machine learning models while preserving data privacy. Despite its advantages, practical FEL deployment faces significant challenges related to device constraints and device-server interactions, necessitating heterogeneous, user-adaptive model training with limited and uncertain communication. In this paper, we introduce FedCache 2.0, a novel personalized FEL architecture that simultaneously addresses these challenges. FedCache 2.0 incorporates the benefits of both dataset distillation and knowledge cache-driven federated learning by storing and organizing distilled data as knowledge in the server-side knowledge cache. Moreover, a device-centric cache sampling strategy is introduced to tailor transferred knowledge for individual devices within controlled communication bandwidth. Extensive experiments on five datasets covering image recognition, audio understanding, and mobile sensor data mining tasks demonstrate that (1) FedCache 2.0 significantly outperforms state-of-the-art methods regardless of model structures, data distributions, and modalities. (2) FedCache 2.0 can train splendid personalized on-device models with at least $\times$28.6 improvement in communication efficiency.

Kentaroh Toyoda, Xiao Wang, Mingzhe Li et al.

Blockchain data analysis is essential for deriving insights, tracking transactions, identifying patterns, and ensuring the integrity and security of decentralized networks. It plays a key role in various areas, such as fraud detection, regulatory compliance, smart contract auditing, and decentralized finance (DeFi) risk management. However, existing blockchain data analysis tools face challenges, including data scarcity, the lack of generalizability, and the lack of reasoning capability. We believe large language models (LLMs) can mitigate these challenges; however, we have not seen papers discussing LLM integration in blockchain data analysis in a comprehensive and systematic way. This paper systematically explores potential techniques and design patterns in LLM-integrated blockchain data analysis. We also outline prospective research opportunities and challenges, emphasizing the need for further exploration in this promising field. This paper aims to benefit a diverse audience spanning academia, industry, and policy-making, offering valuable insights into the integration of LLMs in blockchain data analysis.

Yuhan Tang, Zhiyuan Wu, Bo Gao et al.

Federated Distillation (FD) is a novel and promising distributed machine learning paradigm, where knowledge distillation is leveraged to facilitate a more efficient and flexible cross-device knowledge transfer in federated learning. By optimizing local models with knowledge distillation, FD circumvents the necessity of uploading large-scale model parameters to the central server, simultaneously preserving the raw data on local clients. Despite the growing popularity of FD, there is a noticeable gap in previous works concerning the exploration of poisoning attacks within this framework. This can lead to a scant understanding of the vulnerabilities to potential adversarial actions. To this end, we introduce FDLA, a poisoning attack method tailored for FD. FDLA manipulates logit communications in FD, aiming to significantly degrade model performance on clients through misleading the discrimination of private samples. Through extensive simulation experiments across a variety of datasets, attack scenarios, and FD configurations, we demonstrate that LPA effectively compromises client model accuracy, outperforming established baseline algorithms in this regard. Our findings underscore the critical need for robust defense mechanisms in FD settings to mitigate such adversarial threats.

Zhiyuan Wu, Sheng Sun, Yuwei Wang et al.

The rise of End-Edge-Cloud Collaboration (EECC) offers a promising paradigm for Artificial Intelligence (AI) model training across end devices, edge servers, and cloud data centers, providing enhanced reliability and reduced latency. Hierarchical Federated Learning (HFL) can benefit from this paradigm by enabling multi-tier model aggregation across distributed computing nodes. However, the potential of HFL is significantly constrained by the inherent heterogeneity and dynamic characteristics of EECC environments. Specifically, the uniform model structure bounded by the least powerful end device across all computing nodes imposes a performance bottleneck. Meanwhile, coupled heterogeneity in data distributions and resource capabilities across tiers disrupts hierarchical knowledge transfer, leading to biased updates and degraded performance. Furthermore, the mobility and fluctuating connectivity of computing nodes in EECC environments introduce complexities in dynamic node migration, further compromising the robustness of the training process. To address multiple challenges within a unified framework, we propose End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration (FedEEC), which is a novel EECC-empowered FL framework that allows the trained models from end, edge, to cloud to grow larger in size and stronger in generalization ability. FedEEC introduces two key innovations: (1) Bridge Sample Based Online Distillation Protocol (BSBODP), which enables knowledge transfer between neighboring nodes through generated bridge samples, and (2) Self-Knowledge Rectification (SKR), which refines the transferred knowledge to prevent suboptimal cloud model optimization. The proposed framework effectively handles both cross-tier resource heterogeneity and effective knowledge transfer between neighboring nodes, while satisfying the migration-resilient requirements of EECC.

Zhengyang Shen, Bo Gao, Mayue Shi

Chronic obesity management requires continuous monitoring of energy balance behaviors, yet traditional self-reported methods suffer from significant underreporting and recall bias, and difficulty in integration with modern digital health systems. This study presents COBRA (Chronic Obesity Behavioral Recognition Architecture), a novel deep learning framework for objective behavioral monitoring using wrist-worn multimodal sensors. COBRA integrates a hybrid D-Net architecture combining U-Net spatial modeling, multi-head self-attention mechanisms, and BiLSTM temporal processing to classify daily activities into four obesity-relevant categories: Food Intake, Physical Activity, Sedentary Behavior, and Daily Living. Validated on the WISDM-Smart dataset with 51 subjects performing 18 activities, COBRA's optimal preprocessing strategy combines spectral-temporal feature extraction, achieving high performance across multiple architectures. D-Net demonstrates 96.86% overall accuracy with category-specific F1-scores of 98.55% (Physical Activity), 95.53% (Food Intake), 94.63% (Sedentary Behavior), and 98.68% (Daily Living), outperforming state-of-the-art baselines by 1.18% in accuracy. The framework shows robust generalizability with low demographic variance (<3%), enabling scalable deployment for personalized obesity interventions and continuous lifestyle monitoring.

Bo Gao, Michael W. Spratling

Large language models have achieved remarkable success in recent years, primarily due to the implementation of self-attention mechanisms. However, traditional Softmax attention suffers from numerical instability and reduced performance as the length of inference tokens increases. This paper addresses these issues by proposing a new design principle for attention, viewing it as a two-stage process. We first decompose the Softmax operation into a non-linear positivity transformation and an $l_1$-normalisation step, identifying the latter as essential for maintaining model performance. In the first stage, we replace the standard exponential function with the more numerically stable Softplus activation and introduce a dynamic scale factor based on invariance entropy, creating a novel attention mechanism that outperforms conventional Softmax attention. In the second stage, we introduce a re-weighting mechanism that sharpens the attention distribution, amplifying significant weights while diminishing weaker ones. This enables the model to concentrate more effectively on relevant tokens and fundamentally improves length extrapolation. When combined, this two-stage approach ensures numerical stability and dramatically improves length extrapolation, maintaining a nearly constant validation loss at 16$\times$ the training length while achieving superior results on challenging long-context retrieval tasks and standard downstream benchmarks.

Bo Gao, Jianhui Wang, Xinyuan Song et al.

Current semantic segmentation models typically require a substantial amount of manually annotated data, a process that is both time-consuming and resource-intensive. Alternatively, leveraging advanced text-to-image models such as Midjourney and Stable Diffusion has emerged as an efficient strategy, enabling the automatic generation of synthetic data in place of manual annotations. However, previous methods have been limited to generating single-instance images, as the generation of multiple instances with Stable Diffusion has proven unstable. To address this limitation and expand the scope and diversity of synthetic datasets, we propose a framework \textbf{Free-Mask} that combines a Diffusion Model for segmentation with advanced image editing capabilities, allowing for the integration of multiple objects into images via text-to-image models. Our method facilitates the creation of highly realistic datasets that closely emulate open-world environments while generating accurate segmentation masks. It reduces the labor associated with manual annotation and also ensures precise mask generation. Experimental results demonstrate that synthetic data generated by \textbf{Free-Mask} enables segmentation models to outperform those trained on real data, especially in zero-shot settings. Notably, \textbf{Free-Mask} achieves new state-of-the-art results on previously unseen classes in the VOC 2012 benchmark.

Zhiyuan Wu, Sheng Sun, Yuwei Wang et al.

On-device intelligence (ODI) enables artificial intelligence (AI) applications to run on end devices, providing real-time and customized AI inference without relying on remote servers. However, training models for on-device deployment face significant challenges due to the decentralized and privacy-sensitive nature of users' data, along with end-side constraints related to network connectivity, computation efficiency, etc. Existing training paradigms, such as cloud-based training, federated learning, and transfer learning, fail to sufficiently address these practical constraints that are prevalent for devices. To overcome these challenges, we propose Privacy-Enhanced Training-as-a-Service (PTaaS), a novel service computing paradigm that provides privacy-friendly, customized AI model training for end devices. PTaaS outsources the core training process to remote and powerful cloud or edge servers, efficiently developing customized on-device models based on uploaded anonymous queries, enhancing data privacy while reducing the computation load on individual devices. We explore the definition, goals, and design principles of PTaaS, alongside emerging technologies that support the PTaaS paradigm. An architectural scheme for PTaaS is also presented, followed by a series of open problems that set the stage for future research directions in the field of PTaaS.

Baoming Yan, Lin Wang, Ke Gao et al.

Video affective understanding, which aims to predict the evoked expressions by the video content, is desired for video creation and recommendation. In the recent EEV challenge, a dense affective understanding task is proposed and requires frame-level affective prediction. In this paper, we propose a multi-granularity network with modal attention (MGN-MA), which employs multi-granularity features for better description of the target frame. Specifically, the multi-granularity features could be divided into frame-level, clips-level and video-level features, which corresponds to visual-salient content, semantic-context and video theme information. Then the modal attention fusion module is designed to fuse the multi-granularity features and emphasize more affection-relevant modals. Finally, the fused feature is fed into a Mixtures Of Experts (MOE) classifier to predict the expressions. Further employing model-ensemble post-processing, the proposed method achieves the correlation score of 0.02292 in the EEV challenge.

Jialiang Chang, Bo Gao, Hao Xiao et al.

Ethereum smart contracts are an innovation built on top of the blockchain technology, which provides a platform for automatically executing contracts in an anonymous, distributed, and trusted way. The problem is magnified by the fact that smart contracts, unlike ordinary programs, cannot be patched easily once deployed. It is important for smart contracts to be checked against potential vulnerabilities. In this work, we propose an alternative approach to automatically identify critical program paths (with multiple function calls including inter-contract function calls) in a smart contract, rank the paths according to their criticalness, discard them if they are infeasible or otherwise present them with user friendly warnings for user inspection. We identify paths which involve monetary transaction as critical paths, and prioritize those which potentially violate important properties. For scalability, symbolic execution techniques are only applied to top ranked critical paths. Our approach has been implemented in a tool called sCompile, which has been applied to 36,099 smart contracts. The experiment results show that sCompile is efficient, i.e., 5 seconds on average for one smart contract. Furthermore, we show that many known vulnerabilities can be captured if user inspects as few as 10 program paths generated by sCompile. Lastly, sCompile discovered 224 unknown vulnerabilities with a false positive rate of 15.4% before user inspection.

Kang Zhao, Xi Wang, Mo Yu et al.

Many social networks in our daily life are bipartite networks built on reciprocity. How can we recommend users/friends to a user, so that the user is interested in and attractive to recommended users? In this research, we propose a new collaborative filtering model to improve user recommendations in reciprocal and bipartite social networks. The model considers a user's "taste" in picking others and "attractiveness" in being picked by others. A case study of an online dating network shows that the new model has good performance in recommending both initial and reciprocal contacts.