Yao Wu

Ziye Jia, Yao Wu, Qihui Wu et al.

Unmanned aerial vehicle (UAV) swarms are increasingly explored for their potentials in various applications such as surveillance, disaster response, and military. However, UAV swarms face significant challenges of implementing effective and rapid decisions under dynamic and uncertain environments. The traditional decision-making frameworks, mainly relying on centralized control and rigid architectures, are limited by their adaptability and scalability especially in complex environments. To overcome these challenges, in this paper, we propose a hierarchical Observe-Orient-Decide-Act (H-OODA) loop based framework for the UAV swarm operation in uncertain environments, which is implemented by embedding the classical OODA loop across the cloud-edge-terminal layers, and leveraging the network function virtualization (NFV) technology to provide flexible and scalable decision-making functions. In addition, based on the proposed H-OODA framework, we joint autonomous decision-making and cooperative control to enhance the adaptability and efficiency of UAV swarms. Furthermore, we present some typical case studies to verify the improvement and efficiency of the proposed framework. Finally, the potential challenges and possible directions are analyzed to provide insights for the future H-OODA enabled UAV swarms.

Bochao Liu, Zhipeng Qian, Yang Zhao et al.

Operating and maintaining (O&M) large-scale online engine systems (search, recommendation, advertising) demands substantial human effort for release monitoring, alert response, and root cause analysis. While LLM-based agents are a natural fit for these tasks, the deployment bottleneck is not reasoning capability but orchestration: selecting, for each operational event, the relevant data (metrics, logs, change events) and the applicable operational knowledge (handbook rules and practitioner experience). Feeding all signals indiscriminately causes dilution and hallucination, while manually curating the event-to-(data, knowledge) mapping is intractable under dozens of daily releases. We present Bian Que, an agentic framework with three contributions: (i) a \emph{unified operational paradigm} abstracting day-to-day O&M into three canonical patterns: release interception, proactive inspection, and alert root cause analysis; (ii) \emph{Flexible Skill Arrangement}, where each Skill specifies which data and knowledge to retrieve for a given business-module context and can be automatically generated and updated by LLMs or iteratively refined through natural-language instructions from on-call engineers; (iii) a \emph{unified self-evolving mechanism} in which one correction signal drives two parallel pathways, case-memory-to-knowledge distillation and targeted Skill refinement. Deployed on the e-commerce search engine of KuaiShou, the major short-video platform in China, Bian Que reduces alert volume by 75%, achieves 80% root-cause analysis accuracy, and cuts mean time to resolution by over 50%. Our framework achieves 99.0% pass rate on offline evaluations. Our code is available at https://github.com/benchen4395/BianQue_Assistant.

Yao Wu, Mingwei Xing, Yachao Zhang et al.

In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e.g., synthetic) is adapted to target-domain data (e.g., real-world) without access to target annotation. Previous methods seek to mutually mimic cross-modal outputs in each domain, which enforces a class probability distribution that is agreeable in different domains. However, they overlook the complementarity brought by the heterogeneous fusion in cross-modal learning. In light of this, we propose a novel fusion-then-distillation (FtD++) method to explore cross-modal positive distillation of the source and target domains for 3D semantic segmentation. FtD++ realizes distribution consistency between outputs not only for 2D images and 3D point clouds but also for source-domain and augment-domain. Specially, our method contains three key ingredients. First, we present a model-agnostic feature fusion module to generate the cross-modal fusion representation for establishing a latent space. In this space, two modalities are enforced maximum correlation and complementarity. Second, the proposed cross-modal positive distillation preserves the complete information of multi-modal input and combines the semantic content of the source domain with the style of the target domain, thereby achieving domain-modality alignment. Finally, cross-modal debiased pseudo-labeling is devised to model the uncertainty of pseudo-labels via a self-training manner. Extensive experiments report state-of-the-art results on several domain adaptive scenarios under unsupervised and semi-supervised settings. Code is available at https://github.com/Barcaaaa/FtD-PlusPlus.

Zuo Zuo, Jiahao Dong, Yao Wu et al.

Industrial anomaly classification (AC) is an indispensable task in industrial manufacturing, which guarantees quality and safety of various product. To address the scarcity of data in industrial scenarios, lots of few-shot anomaly detection methods emerge recently. In this paper, we propose an effective few-shot anomaly classification (FSAC) framework with one-stage training, dubbed CLIP-FSAC++. Specifically, we introduce a cross-modality interaction module named Anomaly Descriptor following image and text encoders, which enhances the correlation of visual and text embeddings and adapts the representations of CLIP from pre-trained data to target data. In anomaly descriptor, image-to-text cross-attention module is used to obtain image-specific text embeddings and text-to-image cross-attention module is used to obtain text-specific visual embeddings. Then these modality-specific embeddings are used to enhance original representations of CLIP for better matching ability. Comprehensive experiment results are provided for evaluating our method in few-normal shot anomaly classification on VisA and MVTEC-AD for 1, 2, 4 and 8-shot settings. The source codes are at https://github.com/Jay-zzcoder/clip-fsac-pp

Yao Wu, Kangping Yin, Liang Dong et al.

While Large Language Models (LLMs) excel on standardized medical exams, high scores often fail to translate to high-quality responses for real-world medical queries. Current evaluations rely heavily on multiple-choice questions, failing to capture the unstructured, ambiguous, and long-tail complexities inherent in genuine user inquiries. To bridge this gap, we introduce QuarkMedBench, an ecologically valid benchmark tailored for real-world medical LLM assessment. We compiled a massive dataset spanning Clinical Care, Wellness Health, and Professional Inquiry, comprising 20,821 single-turn queries and 3,853 multi-turn sessions. To objectively evaluate open-ended answers, we propose an automated scoring framework that integrates multi-model consensus with evidence-based retrieval to dynamically generate 220,617 fine-grained scoring rubrics (~9.8 per query). During evaluation, hierarchical weighting and safety constraints structurally quantify medical accuracy, key-point coverage, and risk interception, effectively mitigating the high costs and subjectivity of human grading. Experimental results demonstrate that the generated rubrics achieve a 91.8% concordance rate with clinical expert blind audits, establishing highly dependable medical reliability. Crucially, baseline evaluations on this benchmark reveal significant performance disparities among state-of-the-art models when navigating real-world clinical nuances, highlighting the limitations of conventional exam-based metrics. Ultimately, QuarkMedBench establishes a rigorous, reproducible yardstick for measuring LLM performance on complex health issues, while its framework inherently supports dynamic knowledge updates to prevent benchmark obsolescence.

Zhenxi Zhang, Yanyang Wang, Yao Wu et al.

Developmental Canal Stenosis (DCS) quantification is crucial in cervical spondylosis screening. Compared with quantifying DCS manually, a more efficient and time-saving manner is provided by deep keypoint localization networks, which can be implemented in either the coordinate or the image domain. However, the vertebral visualization features often lead to abnormal topological structures during keypoint localization, including keypoint distortion with edges and weakly connected structures, which cannot be fully suppressed in either the coordinate or image domain alone. To overcome this limitation, a keypoint-edge and a reparameterization modules are utilized to restrict these abnormal structures in a cross-domain manner. The keypoint-edge constraint module restricts the keypoints on the edges of vertebrae, which ensures that the distribution pattern of keypoint coordinates is consistent with those for DCS quantification. And the reparameterization module constrains the weakly connected structures in image-domain heatmaps with coordinates combined. Moreover, the cross-domain network improves spatial generalization by utilizing heatmaps and incorporating coordinates for accurate localization, which avoids the trade-off between these two properties in an individual domain. Comprehensive results of distinct quantification tasks show the superiority and generability of the proposed Topology-inspired Cross-domain Network (TCN) compared with other competing localization methods.

Jie Han, Yixiong Zou, Haozhao Wang et al.

Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.

Yao Wu

Temporal modeling in complex systems requires capturing dependencies across multiple time scales while managing inherent uncertainties. We propose HierCVAE, a novel architecture that integrates hierarchical attention mechanisms with conditional variational autoencoders to address these challenges. HierCVAE employs a three-tier attention structure (local, global, cross-temporal) combined with multi-modal condition encoding to capture temporal, statistical, and trend information. The approach incorporates ResFormer blocks in the latent space and provides explicit uncertainty quantification via prediction heads. Through evaluations on energy consumption datasets, HierCVAE demonstrates a 15-40% improvement in prediction accuracy and superior uncertainty calibration compared to state-of-the-art methods, excelling in long-term forecasting and complex multi-variate dependencies.

Yao Wu

In large language model (LLM) adaptation, balancing multiple optimization objectives such as improving factuality (heat) and increasing confidence (via low entropy) poses a fundamental challenge, especially when prompt parameters (e.g., hidden-layer insertions h and embedding modifications w) interact in non-trivial ways. Existing multi-objective optimization strategies often rely on scalar gradient aggregation, ignoring the deeper geometric structure between objectives and parameters. We propose J6, a structured Jacobian-based method that decomposes the gradient interaction matrix into six interpretable components. This decomposition enables both hard decision-making (e.g., choosing the dominant update direction via argmax) and soft strategies (e.g., attention-style weighting via softmax over J6), forming a dynamic update framework that adapts to local conflict and synergy. Moreover, the interpretable structure of J6 provides insight into parameter attribution, task interference, and geometry-aligned adaptation. Our work introduces a principled and extensible mechanism for conflict-aware prompt optimization, and opens a new avenue for incorporating structured Jacobian reasoning into multi-objective neural tuning.

Ao Li, Bin Yan, Bingfeng Cai et al.

Recent advancements in large language models have significantly accelerated their adoption in healthcare applications, including AI-powered medical consultations, diagnostic report assistance, and medical search tools. However, medical tasks often demand highly specialized knowledge, professional accuracy, and customization capabilities, necessitating a robust and reliable foundation model. QuarkMed addresses these needs by leveraging curated medical data processing, medical-content Retrieval-Augmented Generation (RAG), and a large-scale, verifiable reinforcement learning pipeline to develop a high-performance medical foundation model. The model achieved 70% accuracy on the Chinese Medical Licensing Examination, demonstrating strong generalization across diverse medical benchmarks. QuarkMed offers a powerful yet versatile personal medical AI solution, already serving over millions of users at ai.quark.cn.

Zuo Zuo, Jiahao Dong, Yao Wu et al.

Few-shot anomaly detection methods can effectively address data collecting difficulty in industrial scenarios. Compared to 2D few-shot anomaly detection (2D-FSAD), 3D few-shot anomaly detection (3D-FSAD) is still an unexplored but essential task. In this paper, we propose CLIP3D-AD, an efficient 3D-FSAD method extended on CLIP. We successfully transfer strong generalization ability of CLIP into 3D-FSAD. Specifically, we synthesize anomalous images on given normal images as sample pairs to adapt CLIP for 3D anomaly classification and segmentation. For classification, we introduce an image adapter and a text adapter to fine-tune global visual features and text features. Meanwhile, we propose a coarse-to-fine decoder to fuse and facilitate intermediate multi-layer visual representations of CLIP. To benefit from geometry information of point cloud and eliminate modality and data discrepancy when processed by CLIP, we project and render point cloud to multi-view normal and anomalous images. Then we design multi-view fusion module to fuse features of multi-view images extracted by CLIP which are used to facilitate visual representations for further enhancing vision-language correlation. Extensive experiments demonstrate that our method has a competitive performance of 3D few-shot anomaly classification and segmentation on MVTec-3D AD dataset.

Jie Liu, Yao Wu, Xiaotong Luo et al.

In industrial scenarios, it is crucial not only to identify anomalous items but also to classify the type of anomaly. However, research on anomaly multi-classification remains largely unexplored. This paper proposes a novel and valuable research task called anomaly multi-classification. Given the challenges in applying few-shot learning to this task, due to limited training data and unique characteristics of anomaly images, we introduce a baseline model that combines RelationNet and PatchCore. We propose a data generation method that creates pseudo classes and a corresponding proxy task, aiming to bridge the gap in transferring few-shot learning to industrial scenarios. Furthermore, we utilize contrastive learning to improve the vanilla baseline, achieving much better performance than directly fine-tune a ResNet. Experiments conducted on MvTec AD and MvTec3D AD demonstrate that our approach shows superior performance in this novel task.

Yao Wu, Jian Cao, Guandong Xu et al.

At present, most research on the fairness of recommender systems is conducted either from the perspective of customers or from the perspective of product (or service) providers. However, such a practice ignores the fact that when fairness is guaranteed to one side, the fairness and rights of the other side are likely to reduce. In this paper, we consider recommendation scenarios from the perspective of two sides (customers and providers). From the perspective of providers, we consider the fairness of the providers' exposure in recommender system. For customers, we consider the fairness of the reduced quality of recommendation results due to the introduction of fairness measures. We theoretically analyzed the relationship between recommendation quality, customers fairness, and provider fairness, and design a two-sided fairness-aware recommendation model (TFROM) for both customers and providers. Specifically, we design two versions of TFROM for offline and online recommendation. The effectiveness of the model is verified on three real-world data sets. The experimental results show that TFROM provides better two-sided fairness while still maintaining a higher level of personalization than the baseline algorithms.

Yao Wu, Jian Cao, Guandong Xu

An excessive number of customers often leads to a degradation in service quality. However, the capacity constraints of services are ignored by recommender systems, which may lead to unsatisfactory recommendation. This problem can be solved by limiting the number of users who receive the recommendation for a service, but this may be viewed as unfair. In this paper, we propose a novel metric Top-N Fairness to measure the individual fairness of multi-round recommendations of services with capacity constraints. By considering the fact that users are often only affected by top-ranked items in a recommendation, Top-N Fairness only considers a sub-list consisting of top N services. Based on the metric, we design FAST, a Fairness Assured service recommendation STrategy. FAST adjusts the original recommendation list to provide users with recommendation results that guarantee the long-term fairness of multi-round recommendations. We prove the convergence property of the variance of Top-N Fairness of FAST theoretically. FAST is tested on the Yelp dataset and synthetic datasets. The experimental results show that FAST achieves better recommendation fairness while still maintaining high recommendation quality.

Yao Wu, Tianzhen Wu, Ziyi Xiong et al.

Proliferation of ubiquitous mobile devices makes location based services prevalent. Mobile users are able to volunteer as providers of specific services and in the meanwhile to search these services. For example, drivers may be interested in tracking available nearby users who are willing to help with motor repair or are willing to provide travel directions or first aid. With the diffusion of mobile users, it is necessary to provide scalable means of enabling such users to connect with other nearby users so that they can help each other with specific services. Motivated by these observations, we design and implement a general location based system HelPal for mobile users to provide and enjoy instant service, which is called mobile crowd service. In this demo, we introduce a mobile crowd service system featured with several novel techniques. We sketch the system architecture and illustrate scenarios via several cases. Demonstration shows the user-friendly search interface for users to conveniently find skilled and qualified nearby service providers.

Bin Liu, Yao Wu, Neil Zhenqiang Gong et al.

Advances in smartphone technology have promoted the rapid development of mobile apps. However, the availability of a huge number of mobile apps in application stores has imposed the challenge of finding the right apps to meet the user needs. Indeed, there is a critical demand for personalized app recommendations. Along this line, there are opportunities and challenges posed by two unique characteristics of mobile apps. First, app markets have organized apps in a hierarchical taxonomy. Second, apps with similar functionalities are competing with each other. While there are a variety of approaches for mobile app recommendations, these approaches do not have a focus on dealing with these opportunities and challenges. To this end, in this paper, we provide a systematic study for addressing these challenges. Specifically, we develop a Structural User Choice Model (SUCM) to learn fine-grained user preferences by exploiting the hierarchical taxonomy of apps as well as the competitive relationships among apps. Moreover, we design an efficient learning algorithm to estimate the parameters for the SUCM model. Finally, we perform extensive experiments on a large app adoption data set collected from Google Play. The results show that SUCM consistently outperforms state-of-the-art top-N recommendation methods by a significant margin.