Yanqing Wang
In this paper, we consider the Euler method for backward stochastic Volterra integral equations. First, we approximate the original equation by a family of backward stochastic equations (BSDEs, for short). Then we solve the BSDEs by the Euler method. Finally, by virtue of the numerical solutions to BSDEs, we get the numerical solution to original equation and obtain the global $1/2$ order convergence speed in $L^2$ norm.
Jiqun Pan, Zhenke Duan, Jiani Tu et al.
Industrial question-answering (QA) systems require higher safety and reliability than general-purpose dialogue models, as errors in high-risk scenarios such as equipment fault diagnosis can have severe consequences. Although multi-agent large language models enhance reasoning depth, they suffer from uncontrolled iterations and unverifiable outputs, and conventional distillation methods struggle to transfer collaborative reasoning capabilities to lightweight, deployable student models. To address these challenges, we propose Knowledge Graph-guided Multi-Agent System Distillation (KG-MASD). Our approach formulates distillation as a Markov Decision Process and incorporates a knowledge graph as a verifiable structured prior to enrich state representation and ensure convergence. By integrating collaborative reasoning with knowledge grounding, KG-MASD generates high-confidence instruction-tuning data and jointly distills reasoning depth and verifiability into compact student models suitable for edge deployment. Experiments on an industrial QA dataset show that KG-MASD improves accuracy by 2.4 per cent to 20.1 per cent over baselines and significantly enhances reliability, enabling trustworthy AI deployment in safety-critical industrial scenarios. Code and data are available at https://github.com/erwinmsmith/KG-MAD/.
Zhenke Duan, Jiqun Pan, Jiani Tu et al.
In the era of large-scale artificial intelligence, Large Language Models (LLMs) have made significant strides in natural language processing. However, they often lack transparency and generate unreliable outputs, raising concerns about their interpretability. To address this, the Chain of Thought (CoT) prompting method structures reasoning into step-by-step deductions. Yet, not all reasoning chains are valid, and errors can lead to unreliable conclusions. We propose ECCoT, an End-to-End Cognitive Chain of Thought Validation Framework, to evaluate and refine reasoning chains in LLMs. ECCoT integrates the Markov Random Field-Embedded Topic Model (MRF-ETM) for topic-aware CoT generation and Causal Sentence-BERT (CSBert) for causal reasoning alignment. By filtering ineffective chains using structured ordering statistics, ECCoT improves interpretability, reduces biases, and enhances the trustworthiness of LLM-based decision-making. Key contributions include the introduction of ECCoT, MRF-ETM for topic-driven CoT generation, and CSBert for causal reasoning enhancement. Code is released at: https://github.com/erwinmsmith/ECCoT.git.
Zhe Xin, Yinghao Cai, Tao Lu et al.
We address the problem of visual place recognition with perceptual changes. The fundamental problem of visual place recognition is generating robust image representations which are not only insensitive to environmental changes but also distinguishable to different places. Taking advantage of the feature extraction ability of Convolutional Neural Networks (CNNs), we further investigate how to localize discriminative visual landmarks that positively contribute to the similarity measurement, such as buildings and vegetations. In particular, a Landmark Localization Network (LLN) is designed to indicate which regions of an image are used for discrimination. Detailed experiments are conducted on open source datasets with varied appearance and viewpoint changes. The proposed approach achieves superior performance against state-of-the-art methods.
Yanqing Wang, Chong Wang, Xiaojie Li et al.
With the rapid increasing of software project size and maintenance cost, adherence to coding standards especially by managing identifier naming, is attracting a pressing concern from both computer science educators and software managers. Software developers mainly use identifier names to represent the knowledge recorded in source code. However, the popularity and adoption consistency of identifier naming conventions have not been revealed yet in this field. Taking forty-eight popular open source projects written in three top-ranking programming languages Java, C and C++ as examples, an identifier extraction tool based on regular expression matching is developed. In the subsequent investigation, some interesting findings are obtained. For the identifier naming popularity, it is found that Camel and Pascal naming conventions are leading the road while Hungarian notation is vanishing. For the identifier naming consistency, we have found that the projects written in Java have a much better performance than those written in C and C++. Finally, academia and software industry are urged to adopt the most popular naming conventions consistently in their practices so as to lead the identifier naming to a standard, unified and high-quality road.
Qikui Zhu, Yihui Bi, Danxin Wang et al.
Heatmap-based anatomical landmark detection is still facing two unresolved challenges: 1) inability to accurately evaluate the distribution of heatmap; 2) inability to effectively exploit global spatial structure information. To address the computational inability challenge, we propose a novel position-aware and sample-aware central loss. Specifically, our central loss can absorb position information, enabling accurate evaluation of the heatmap distribution. More advanced is that our central loss is sample-aware, which can adaptively distinguish easy and hard samples and make the model more focused on hard samples while solving the challenge of extreme imbalance between landmarks and non-landmarks. To address the challenge of ignoring structure information, a Coordinated Transformer, called CoorTransformer, is proposed, which establishes long-range dependencies under the guidance of landmark coordination information, making the attention more focused on the sparse landmarks while taking advantage of global spatial structure. Furthermore, CoorTransformer can speed up convergence, effectively avoiding the defect that Transformers have difficulty converging in sparse representation learning. Using the advanced CoorTransformer and central loss, we propose a generalized detection model that can handle various scenarios, inherently exploiting the underlying relationship between landmarks and incorporating rich structural knowledge around the target landmarks. We analyzed and evaluated CoorTransformer and central loss on three challenging landmark detection tasks. The experimental results show that our CoorTransformer outperforms state-of-the-art methods, and the central loss significantly improves the performance of the model with p-values< 0.05.
Miao Zhang, Xiaofei Kang, Yanqing Wang et al.
Trivial events are ubiquitous in human to human conversations, e.g., cough, laugh and sniff. Compared to regular speech, these trivial events are usually short and unclear, thus generally regarded as not speaker discriminative and so are largely ignored by present speaker recognition research. However, these trivial events are highly valuable in some particular circumstances such as forensic examination, as they are less subjected to intentional change, so can be used to discover the genuine speaker from disguised speech. In this paper, we collect a trivial event speech database that involves 75 speakers and 6 types of events, and report preliminary speaker recognition results on this database, by both human listeners and machines. Particularly, the deep feature learning technique recently proposed by our group is utilized to analyze and recognize the trivial events, which leads to acceptable equal error rates (EERs) despite the extremely short durations (0.2-0.5 seconds) of these events. Comparing different types of events, 'hmm' seems more speaker discriminative.
Yanqing Wang, Hong Ge, Xiaojing Feng et al.
Cooperative learning theory has shown that stable membership is a hallmark of effective work teams. According to relation strength and social network centrality, this paper proposes an approach to measure team stability reasons in consecutive cooperative learning. Taking consecutive course projects of software engineering in a university as examples, we examine the relation between team stability and learning performance in consecutive cooperative learning from two parts: learning score and learning satisfaction. Through empirical analysis, it arrives at the conclusion that learning score is in weak positive correlation with team stability. Through questionnaire and interviews, it finds out 78% of the students did not value the importance of team stability, and 67% of the teachers never recommend the students to keep stable teams. Finally, we put forward an expected correlation model of learning performance as future work and discuss instability as well.