Behavior recognition of Hu sheep contributes to their intensive and intelligent farming.Due to the generally high density of Hu sheep farming,severe occlusion occurs among different behaviors and even among sheep perf...Behavior recognition of Hu sheep contributes to their intensive and intelligent farming.Due to the generally high density of Hu sheep farming,severe occlusion occurs among different behaviors and even among sheep performing the same behavior,leading to missing and false detection issues in existing behavior recognition methods.A high-low frequency aggregated attention and negative sample comprehensive score loss and comprehensive score soft non-maximum suppression-YOLO(HLNC-YOLO)was proposed for identifying the behavior of Hu sheep,addressing the issues of missed and erroneous detections caused by occlusion between Hu sheep in intensive farming.Firstly,images of four typical behaviors-standing,lying,eating,and drinking-were collected from the sheep farm to construct the Hu sheep behavior dataset(HSBD).Next,to solve the occlusion issues,during the training phase,the C2F-HLAtt module was integrated,which combined high-low frequency aggregation attention,into the YOLO v8 Backbone to perceive occluded objects and introduce an auxiliary reversible branch to retain more effective features.Using comprehensive score regression loss(CSLoss)to reduce the scores of suboptimal boxes and enhance the comprehensive scores of occluded object boxes.Finally,the soft comprehensive score non-maximal suppression(Soft-CS-NMS)algorithm filtered prediction boxes during the inferencing.Testing on the HSBD,HLNC-YOLO achieved a mean average precision(mAP@50)of 87.8%,with a memory footprint of 17.4 MB.This represented an improvement of 7.1,2.2,4.6,and 11 percentage points over YOLO v8,YOLO v9,YOLO v10,and Faster R-CNN,respectively.Research indicated that the HLNC-YOLO accurately identified the behavior of Hu sheep in intensive farming and possessed generalization capabilities,providing technical support for smart farming.展开更多
Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLM...Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLMs.Therefore,in order to better assess the capability of LLMs in the agricultural domain,Agri-Eval was proposed as a benchmark for assessing the knowledge and reasoning ability of LLMs in agriculture.The assessment dataset used in Agri-Eval covered seven major disciplines in the agricultural domain:crop science,horticulture,plant protection,animal husbandry,forest science,aquaculture science,and grass science,and contained a total of 2283 questions.Among domestic general-purpose LLMs,DeepSeek R1 performed best with an accuracy rate of 75.49%.In the realm of international general-purpose LLMs,Gemini 2.0 pro exp 0205 standed out as the top performer,achieving an accuracy rate of 74.28%.As an LLMs in agriculture vertical,Shennong V2.0 outperformed all the LLMs in China,and the answer accuracy rate of agricultural knowledge exceeded that of all the existing general-purpose LLMs.The launch of Agri-Eval helped the LLM developers to comprehensively evaluate the model's capability in the field of agriculture through a variety of tasks and tests to promote the development of the LLMs in the field of agriculture.展开更多
To investigate the influence of Al-Zn-Mg-Cu alloy with as-homogenized and as-rolled initial microstructures on the tensile flow behavior,isothermal tensile tests were conducted on a GLEEBLE-3500 isothermal simulator a...To investigate the influence of Al-Zn-Mg-Cu alloy with as-homogenized and as-rolled initial microstructures on the tensile flow behavior,isothermal tensile tests were conducted on a GLEEBLE-3500 isothermal simulator at temperatures of 380-440℃and strain rates of 0.05-1 s^(−1).The Johnson-Cook model,Hensel-Spittel model,strain-compensated Arrhenius model,and critical fracture strain model were established.Results show that through the evaluation of the models using the correlation coefficient(R)and the average absolute relative error,the strain-compensated Arrhenius model can represent the flow behavior of the alloy more accurately.Shear bands are more pronounced in the as-homogenized specimens,whereas dynamic recrystallization is predominantly observed in as-rolled specimens.Fracture morphology analysis reveals that a mixed fracture mechanism is prevalent in the as-homogenized specimen,whereas a ductile fracture mechanism is predominant in the as-rolled specimen.The processing maps indicate that the unstable region is reduced in the as-rolled specimens compared with that in the as-homogenized specimens.The optimal hot working windows for the as-homogenized and as-rolled specimens are determined as 410-440℃/0.14-1 s^(−1)and 380-400℃/0.05-0.29 s^(−1),respectively.展开更多
Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remain...Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remains one of the security challenges. is paper proposes LinguTimeX,a new framework that combines natural language processing with arti cial intelligence,along with explainable Arti cial Intelligence(AI)not only to detect CTC but also to provide insights into the decision process.LinguTimeX performs multidimensional feature extraction by fusing linguistic attributes with temporal network patterns to identify covert channels precisely.LinguTimeX demonstrates strong e ectiveness in detecting CTC across multiple languages;namely English,Arabic,and Chinese.Speci cally,the LSTM and RNN models achieved F1 scores of 90%on the English dataset,89%on the Arabic dataset,and 88%on the Chinese dataset,showcasing their superior performance and ability to generalize across multiple languages. is highlights their robustness in detecting CTCs within security systems,regardless of the language or cultural context of the data.In contrast,the DeepForest model produced F1-scores ranging from 86%to 87%across the same datasets,further con rming its e ectiveness in CTC detection.Although other algorithms also showed reasonable accuracy,the LSTM and RNN models consistently outperformed them in multilingual settings,suggesting that deep learning models might be better suited for this particular problem.展开更多
Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interact...Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.展开更多
Correction to:Nano-Micro Letters(2026)18:10.https://doi.org/10.1007/s40820-025-01852-8 Following publication of the original article[1],the authors reported that the last author’s name was inadvertently misspelled.Th...Correction to:Nano-Micro Letters(2026)18:10.https://doi.org/10.1007/s40820-025-01852-8 Following publication of the original article[1],the authors reported that the last author’s name was inadvertently misspelled.The published version showed“Hongzhen Chen”,whereas the correct spelling should be“Hongzheng Chen”.The correct author name has been provided in this Correction,and the original article[1]has been corrected.展开更多
The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in S...The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.展开更多
Residential energy-use behavior and energy-saving awareness play a crucial role in sustainable urban energy planning and building energy efficiency,particularly under the pressures of climate change.However,existing s...Residential energy-use behavior and energy-saving awareness play a crucial role in sustainable urban energy planning and building energy efficiency,particularly under the pressures of climate change.However,existing studies often lack comparative analysis of urban-rural differences and tend to focus excessively on behavior patterns while neglecting the dimension of energysaving awareness.With China’s urbanization rate reaching 66.16%,understanding such regional disparities has become increasingly important.To address these research gaps,this study conducts a large-scale survey on space cooling behaviors among residents in Beijing,a representative Chinese megacity.It should be noted that living standards in such megacities are generally higher than the national average,which may shape distinctive energy-use profiles.Analyzing 1573valid samples(1064 urban/442 rural)in 2024,this study employed K-Prototypes and K-Modes clustering to identify typical cooling behavior and energy-saving awareness pattems,followed by Kendall/Chi-square correlation tests and XGBoost importance analysis to determine key influencing factors,with subsequent urban-rural comparative analysis.Results indicate that urban residents are primarily heat-sensitive or heat-tolerant,with a secondary patten of mid-low temperature preference,and generally exhibit long cooling durations;rural behavior is dominated by heat-tolerant type,followed by heat-sensitive,mid-low temperature preference,and never-on types as secondary patterns;both urban and rural areas exhibit energy-savingawareness characterized by low consumption-lowwillingness,though urban areas show marginally higher motivation;energy-saving awareness correlates with cooling behavior in rural areas,but this relationship weakens significantly in urban contexts.展开更多
This paper undertakes a systematic combing of the development of research on integrating Chinese culture into foreign language education in China from the 1980s to 2025,dividing it into three stages:cultural attachmen...This paper undertakes a systematic combing of the development of research on integrating Chinese culture into foreign language education in China from the 1980s to 2025,dividing it into three stages:cultural attachment,cultural compensation,and cultural symbiosis,and reveals the logical shift of the research from the dominance of target language culture to the construction of the subjectivity of Chinese culture.Through quantitative and qualitative analysis of 435 CSSCI papers,three core themes are extracted:what to integrate,why to integrate,and how to integrate.This paper critically analyzes three pairs of contradictions:the imbalance between instrumentality and humanism,the separation of national narrative and individual expression,and the disconnection between traditional inheritance and modern transformation.It is proposed that future research should reconstruct the educational logic based on the Chinese context,integrate the national and individual dimensions,and build a dialogue mechanism between tradition and modernity,so as to provide theoretical and practical reference for the construction of a foreign language education system with Chinese characteristics.展开更多
With the rapid development of smart manufacturing,intelligent safety monitoring in industrial workshops has become increasingly important.To address the challenges of complex backgrounds,target scale variation,and exc...With the rapid development of smart manufacturing,intelligent safety monitoring in industrial workshops has become increasingly important.To address the challenges of complex backgrounds,target scale variation,and excessive model parameters in worker violation detection,this study proposes ADCP-YOLO,an enhanced lightweight model based on YOLOv8.Here,“ADCP”represents four key improvements:Alterable Kernel Convolution(AKConv),Dilated-Wise Residual(DWR)module,Channel Reconstruction Global Attention Mechanism(CRGAM),and Powerful-IoU loss.These components collaboratively enhance feature extraction,multi-scale perception,and localization accuracy while effectively reducing model complexity and computational cost.Experimental results show that ADCP-YOLO achieves a mAP of 90.6%,surpassing YOLOv8 by 3.0%with a 6.6%reduction in parameters.These findings demonstrate that ADCP-YOLO successfully balances accuracy and efficiency,offering a practical solution for intelligent safety monitoring in smart factory workshops.展开更多
This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to use...This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.展开更多
This study utilizes wet/dry cyclic corrosion testing combined with corrosion big data technology to investigate the mechanism by which chloride ions(Cl^(-))influence the corrosion behavior of 650 MPa high-strength low...This study utilizes wet/dry cyclic corrosion testing combined with corrosion big data technology to investigate the mechanism by which chloride ions(Cl^(-))influence the corrosion behavior of 650 MPa high-strength low-alloy(HSLA)steel in industrially polluted environments.The corrosion process of 650 MPa HSLA steel occurred in two distinct stages:an initial corrosion stage and a stable corrosion stage.During the initial phase,the weight loss rate increased rapidly owing to the instability of the rust layer.Notably,this study demonstrated that 650 MPa HSLA steel exhibited superior corrosion resistance in Cl-containing environments.The formation of a corrosion-product film eventually reduced the weight-loss rate.However,the intrusion of Cl^(-)at increasing concentrations gradually destabilized theα/γ^(*)phases of the rust layer,leading to a looser structure and lower polarization resistance(R_(p)).The application of corrosion big data technology in this study facilitated the validation and analysis of the experimental results,offering new insights into the corrosion mechanisms of HSLA steel in chloride-rich environments.展开更多
The volume change behavior of natural gas hydrate-bearing sediment is essential as it influences settlement,strength,and stiffness,which directly affect the stability of hydrate reservoirs during hydrate extraction or...The volume change behavior of natural gas hydrate-bearing sediment is essential as it influences settlement,strength,and stiffness,which directly affect the stability of hydrate reservoirs during hydrate extraction or in response to environmental changes.The volume change is influenced not only by stress but also by the formation and dissociation of hydrates.This study adopted a customized apparatus for one-dimensional compression tests,allowing independent control of gas pressure and effective stress.Tests were conducted on samples with different hydrate saturations along various temperature-gas pressure-effective stress paths,yielding some conclusions related to compressibility and creep.An unusual phenomenon was observed under low-stress conditions:hydrate formation led to shrinkage rather than expansion.Three potential mechanisms behind this occurrence were discussed.As hydrate saturation increases,the yield stress rises while the compression and swelling indexes remain minimally affected.After hydrate dissociation,the compression curve of hydrate-bearing sediment drops to that of hydrate-free sediment.Once hydrate is formed,the compression curve of hydrate-free sediment gradually approaches that of hydrate-bearing sediment during the subsequent loading.Under low-stress conditions,the creep of both hydrate-free and hydrate-bearing sediments is very weak.However,when stress increases,significantly beyond the yield stress,the creep of both sediments increases significantly,with hydrate-bearing sediment exhibiting much greater creep than hydrate-free sediment.展开更多
Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Re...Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.展开更多
War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient an...War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.展开更多
This interview examines the theoretical foundations,pedagogical applications,developmental trajectory,and future directions of the xu-argument.Professor Wang Chuming offers a comprehensive account of the xu-argument,c...This interview examines the theoretical foundations,pedagogical applications,developmental trajectory,and future directions of the xu-argument.Professor Wang Chuming offers a comprehensive account of the xu-argument,clarifying its theoretical framework,the learning mechanisms underlying xu,and its interface with international theories of second language acquisition(SLA).From the perspective of the xu-argument,he proposes novel interpretations of core issues in SLA.Drawing on the development of the xu-argument,Wang further discusses the essence,directions,and methodology of innovation in SLA theory.He emphasizes that theoretical advances must capture and illuminate underlying natural laws,arguing that innovative approaches are typically rooted in deep reflection on common sense.He also calls for theoretical innovation in SLA in the Chinese context,advocating a robust research paradigm that shifts from local observation to global theoretical generalization,thereby promoting bottom-up theoretical development.In closing,he highlights the promising prospects for SLA theory in the era of artificial intelligence.展开更多
Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that man...Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.展开更多
Drilling and blasting tunneling is a cyclic process in which tunnel rock undergoes repeated blast loading,affecting its dynamic characteristics,energy evolution,and damage progression.To explore the dynamic mechanical...Drilling and blasting tunneling is a cyclic process in which tunnel rock undergoes repeated blast loading,affecting its dynamic characteristics,energy evolution,and damage progression.To explore the dynamic mechanical properties and damage mechanisms of carbonaceous slate under cyclic impact loads of varying intensities,cyclic dynamic tests are conducted using a triaxial split Hopkinson pressure bar.This study analyzes the stress-strain relationship,energy damage evolution,and macro-to-micro failure characteristics.The results show that peak stress and strain are significantly influenced by impact intensity and the number of impacts.The initial dynamic stress is positively correlated with the impact intensity,but with more impact,the dynamic stress decreases while the peak strain increases.Energy evolution follows a pattern of"slow growthfluctuating growthrapid growth,"with the crack initiation stress and its proportion decreasing.CT and SEM analyses reveal that as the impact intensity increases,failure becomes more chaotic,the fracture volume increases,and the fracture mode shifts from interlayer and intergranular to through-layer and trans-granular fractures.These findings provide an experimental basis for soft rock tunnel stability analysis.展开更多
文摘Behavior recognition of Hu sheep contributes to their intensive and intelligent farming.Due to the generally high density of Hu sheep farming,severe occlusion occurs among different behaviors and even among sheep performing the same behavior,leading to missing and false detection issues in existing behavior recognition methods.A high-low frequency aggregated attention and negative sample comprehensive score loss and comprehensive score soft non-maximum suppression-YOLO(HLNC-YOLO)was proposed for identifying the behavior of Hu sheep,addressing the issues of missed and erroneous detections caused by occlusion between Hu sheep in intensive farming.Firstly,images of four typical behaviors-standing,lying,eating,and drinking-were collected from the sheep farm to construct the Hu sheep behavior dataset(HSBD).Next,to solve the occlusion issues,during the training phase,the C2F-HLAtt module was integrated,which combined high-low frequency aggregation attention,into the YOLO v8 Backbone to perceive occluded objects and introduce an auxiliary reversible branch to retain more effective features.Using comprehensive score regression loss(CSLoss)to reduce the scores of suboptimal boxes and enhance the comprehensive scores of occluded object boxes.Finally,the soft comprehensive score non-maximal suppression(Soft-CS-NMS)algorithm filtered prediction boxes during the inferencing.Testing on the HSBD,HLNC-YOLO achieved a mean average precision(mAP@50)of 87.8%,with a memory footprint of 17.4 MB.This represented an improvement of 7.1,2.2,4.6,and 11 percentage points over YOLO v8,YOLO v9,YOLO v10,and Faster R-CNN,respectively.Research indicated that the HLNC-YOLO accurately identified the behavior of Hu sheep in intensive farming and possessed generalization capabilities,providing technical support for smart farming.
文摘Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLMs.Therefore,in order to better assess the capability of LLMs in the agricultural domain,Agri-Eval was proposed as a benchmark for assessing the knowledge and reasoning ability of LLMs in agriculture.The assessment dataset used in Agri-Eval covered seven major disciplines in the agricultural domain:crop science,horticulture,plant protection,animal husbandry,forest science,aquaculture science,and grass science,and contained a total of 2283 questions.Among domestic general-purpose LLMs,DeepSeek R1 performed best with an accuracy rate of 75.49%.In the realm of international general-purpose LLMs,Gemini 2.0 pro exp 0205 standed out as the top performer,achieving an accuracy rate of 74.28%.As an LLMs in agriculture vertical,Shennong V2.0 outperformed all the LLMs in China,and the answer accuracy rate of agricultural knowledge exceeded that of all the existing general-purpose LLMs.The launch of Agri-Eval helped the LLM developers to comprehensively evaluate the model's capability in the field of agriculture through a variety of tasks and tests to promote the development of the LLMs in the field of agriculture.
文摘To investigate the influence of Al-Zn-Mg-Cu alloy with as-homogenized and as-rolled initial microstructures on the tensile flow behavior,isothermal tensile tests were conducted on a GLEEBLE-3500 isothermal simulator at temperatures of 380-440℃and strain rates of 0.05-1 s^(−1).The Johnson-Cook model,Hensel-Spittel model,strain-compensated Arrhenius model,and critical fracture strain model were established.Results show that through the evaluation of the models using the correlation coefficient(R)and the average absolute relative error,the strain-compensated Arrhenius model can represent the flow behavior of the alloy more accurately.Shear bands are more pronounced in the as-homogenized specimens,whereas dynamic recrystallization is predominantly observed in as-rolled specimens.Fracture morphology analysis reveals that a mixed fracture mechanism is prevalent in the as-homogenized specimen,whereas a ductile fracture mechanism is predominant in the as-rolled specimen.The processing maps indicate that the unstable region is reduced in the as-rolled specimens compared with that in the as-homogenized specimens.The optimal hot working windows for the as-homogenized and as-rolled specimens are determined as 410-440℃/0.14-1 s^(−1)and 380-400℃/0.05-0.29 s^(−1),respectively.
基金This study is financed by the European Union-NextGenerationEU,through the National Recovery and Resilience Plan of the Republic of Bulgaria,Project No.BG-RRP-2.013-0001.
文摘Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remains one of the security challenges. is paper proposes LinguTimeX,a new framework that combines natural language processing with arti cial intelligence,along with explainable Arti cial Intelligence(AI)not only to detect CTC but also to provide insights into the decision process.LinguTimeX performs multidimensional feature extraction by fusing linguistic attributes with temporal network patterns to identify covert channels precisely.LinguTimeX demonstrates strong e ectiveness in detecting CTC across multiple languages;namely English,Arabic,and Chinese.Speci cally,the LSTM and RNN models achieved F1 scores of 90%on the English dataset,89%on the Arabic dataset,and 88%on the Chinese dataset,showcasing their superior performance and ability to generalize across multiple languages. is highlights their robustness in detecting CTCs within security systems,regardless of the language or cultural context of the data.In contrast,the DeepForest model produced F1-scores ranging from 86%to 87%across the same datasets,further con rming its e ectiveness in CTC detection.Although other algorithms also showed reasonable accuracy,the LSTM and RNN models consistently outperformed them in multilingual settings,suggesting that deep learning models might be better suited for this particular problem.
基金supported by the National Key R&D Program of China[2022YFF0902703]the State Administration for Market Regulation Science and Technology Plan Project(2024MK033).
文摘Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.
文摘Correction to:Nano-Micro Letters(2026)18:10.https://doi.org/10.1007/s40820-025-01852-8 Following publication of the original article[1],the authors reported that the last author’s name was inadvertently misspelled.The published version showed“Hongzhen Chen”,whereas the correct spelling should be“Hongzheng Chen”.The correct author name has been provided in this Correction,and the original article[1]has been corrected.
基金the research project LaTe4PoliticES(PID2022-138099OB-I00)funded by MCIN/AEI/10.13039/501100011033 and the European Fund for Regional Development(ERDF)-a way to make Europe.Tomás Bernal-Beltrán is supported by University of Murcia through the predoctoral programme.
文摘The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.
文摘Residential energy-use behavior and energy-saving awareness play a crucial role in sustainable urban energy planning and building energy efficiency,particularly under the pressures of climate change.However,existing studies often lack comparative analysis of urban-rural differences and tend to focus excessively on behavior patterns while neglecting the dimension of energysaving awareness.With China’s urbanization rate reaching 66.16%,understanding such regional disparities has become increasingly important.To address these research gaps,this study conducts a large-scale survey on space cooling behaviors among residents in Beijing,a representative Chinese megacity.It should be noted that living standards in such megacities are generally higher than the national average,which may shape distinctive energy-use profiles.Analyzing 1573valid samples(1064 urban/442 rural)in 2024,this study employed K-Prototypes and K-Modes clustering to identify typical cooling behavior and energy-saving awareness pattems,followed by Kendall/Chi-square correlation tests and XGBoost importance analysis to determine key influencing factors,with subsequent urban-rural comparative analysis.Results indicate that urban residents are primarily heat-sensitive or heat-tolerant,with a secondary patten of mid-low temperature preference,and generally exhibit long cooling durations;rural behavior is dominated by heat-tolerant type,followed by heat-sensitive,mid-low temperature preference,and never-on types as secondary patterns;both urban and rural areas exhibit energy-savingawareness characterized by low consumption-lowwillingness,though urban areas show marginally higher motivation;energy-saving awareness correlates with cooling behavior in rural areas,but this relationship weakens significantly in urban contexts.
基金“A Study on the Value and Path of Integrating Excellent Traditional Chinese Culture Into Intercultural Communication Courses”(ZD2024)a project by the Beijing Higher Education Association,as well as“A Study on the Path of Empowering the Integration of Excellent Traditional Chinese Culture Into Intercultural Communication Courses With Generative AI”(2024),an institutional project of Beijing International Studies University.
文摘This paper undertakes a systematic combing of the development of research on integrating Chinese culture into foreign language education in China from the 1980s to 2025,dividing it into three stages:cultural attachment,cultural compensation,and cultural symbiosis,and reveals the logical shift of the research from the dominance of target language culture to the construction of the subjectivity of Chinese culture.Through quantitative and qualitative analysis of 435 CSSCI papers,three core themes are extracted:what to integrate,why to integrate,and how to integrate.This paper critically analyzes three pairs of contradictions:the imbalance between instrumentality and humanism,the separation of national narrative and individual expression,and the disconnection between traditional inheritance and modern transformation.It is proposed that future research should reconstruct the educational logic based on the Chinese context,integrate the national and individual dimensions,and build a dialogue mechanism between tradition and modernity,so as to provide theoretical and practical reference for the construction of a foreign language education system with Chinese characteristics.
基金TheNationalNatural Science Foundation ofChina(Nos.62272418,62102058)Zhejiang Provincial Natural Science Foundation Major Project(No.LD24F020004)the Major Open Project of Key Laboratory for Advanced Design and Intelligent Computing of the Ministry of Education(No.ADIC2023ZD001).
文摘With the rapid development of smart manufacturing,intelligent safety monitoring in industrial workshops has become increasingly important.To address the challenges of complex backgrounds,target scale variation,and excessive model parameters in worker violation detection,this study proposes ADCP-YOLO,an enhanced lightweight model based on YOLOv8.Here,“ADCP”represents four key improvements:Alterable Kernel Convolution(AKConv),Dilated-Wise Residual(DWR)module,Channel Reconstruction Global Attention Mechanism(CRGAM),and Powerful-IoU loss.These components collaboratively enhance feature extraction,multi-scale perception,and localization accuracy while effectively reducing model complexity and computational cost.Experimental results show that ADCP-YOLO achieves a mAP of 90.6%,surpassing YOLOv8 by 3.0%with a 6.6%reduction in parameters.These findings demonstrate that ADCP-YOLO successfully balances accuracy and efficiency,offering a practical solution for intelligent safety monitoring in smart factory workshops.
基金funded by the Office of the Vice-President for Research and Development of Cebu Technological University.
文摘This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.
基金financially supported by the National Natural Science Foundation of China(Nos.52104319 and 52374323)。
文摘This study utilizes wet/dry cyclic corrosion testing combined with corrosion big data technology to investigate the mechanism by which chloride ions(Cl^(-))influence the corrosion behavior of 650 MPa high-strength low-alloy(HSLA)steel in industrially polluted environments.The corrosion process of 650 MPa HSLA steel occurred in two distinct stages:an initial corrosion stage and a stable corrosion stage.During the initial phase,the weight loss rate increased rapidly owing to the instability of the rust layer.Notably,this study demonstrated that 650 MPa HSLA steel exhibited superior corrosion resistance in Cl-containing environments.The formation of a corrosion-product film eventually reduced the weight-loss rate.However,the intrusion of Cl^(-)at increasing concentrations gradually destabilized theα/γ^(*)phases of the rust layer,leading to a looser structure and lower polarization resistance(R_(p)).The application of corrosion big data technology in this study facilitated the validation and analysis of the experimental results,offering new insights into the corrosion mechanisms of HSLA steel in chloride-rich environments.
基金supported by the National Natural Science Foundation of China(Grant No.42171135)the Science and Technology Program of CNOOC Research Institute(Grant No.2023OTKK03)the“CUG Scholar”Scientific Research Funds at China University of Geosciences(Project No.2022098).
文摘The volume change behavior of natural gas hydrate-bearing sediment is essential as it influences settlement,strength,and stiffness,which directly affect the stability of hydrate reservoirs during hydrate extraction or in response to environmental changes.The volume change is influenced not only by stress but also by the formation and dissociation of hydrates.This study adopted a customized apparatus for one-dimensional compression tests,allowing independent control of gas pressure and effective stress.Tests were conducted on samples with different hydrate saturations along various temperature-gas pressure-effective stress paths,yielding some conclusions related to compressibility and creep.An unusual phenomenon was observed under low-stress conditions:hydrate formation led to shrinkage rather than expansion.Three potential mechanisms behind this occurrence were discussed.As hydrate saturation increases,the yield stress rises while the compression and swelling indexes remain minimally affected.After hydrate dissociation,the compression curve of hydrate-bearing sediment drops to that of hydrate-free sediment.Once hydrate is formed,the compression curve of hydrate-free sediment gradually approaches that of hydrate-bearing sediment during the subsequent loading.Under low-stress conditions,the creep of both hydrate-free and hydrate-bearing sediments is very weak.However,when stress increases,significantly beyond the yield stress,the creep of both sediments increases significantly,with hydrate-bearing sediment exhibiting much greater creep than hydrate-free sediment.
文摘Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.
文摘War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.
文摘This interview examines the theoretical foundations,pedagogical applications,developmental trajectory,and future directions of the xu-argument.Professor Wang Chuming offers a comprehensive account of the xu-argument,clarifying its theoretical framework,the learning mechanisms underlying xu,and its interface with international theories of second language acquisition(SLA).From the perspective of the xu-argument,he proposes novel interpretations of core issues in SLA.Drawing on the development of the xu-argument,Wang further discusses the essence,directions,and methodology of innovation in SLA theory.He emphasizes that theoretical advances must capture and illuminate underlying natural laws,arguing that innovative approaches are typically rooted in deep reflection on common sense.He also calls for theoretical innovation in SLA in the Chinese context,advocating a robust research paradigm that shifts from local observation to global theoretical generalization,thereby promoting bottom-up theoretical development.In closing,he highlights the promising prospects for SLA theory in the era of artificial intelligence.
基金supported by 2023 Higher Education Scientific Research Planning Project of China Society of Higher Education(No.23PG0408)2023 Philosophy and Social Science Research Programs in Jiangsu Province(No.2023SJSZ0993)+2 种基金Nantong Science and Technology Project(No.JC2023070)Key Project of Jiangsu Province Education Science 14th Five-Year Plan(Grant No.B-b/2024/02/41)the Open Fund of Advanced Cryptography and System Security Key Laboratory of Sichuan Province(Grant No.SKLACSS-202407).
文摘Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.
基金support from the Joint Funds of the National Natural Science Foundation of China(Grant No.U23A2060)the National Natural Science Foundation of China(Grant Nos.42177143 and 52474150).
文摘Drilling and blasting tunneling is a cyclic process in which tunnel rock undergoes repeated blast loading,affecting its dynamic characteristics,energy evolution,and damage progression.To explore the dynamic mechanical properties and damage mechanisms of carbonaceous slate under cyclic impact loads of varying intensities,cyclic dynamic tests are conducted using a triaxial split Hopkinson pressure bar.This study analyzes the stress-strain relationship,energy damage evolution,and macro-to-micro failure characteristics.The results show that peak stress and strain are significantly influenced by impact intensity and the number of impacts.The initial dynamic stress is positively correlated with the impact intensity,but with more impact,the dynamic stress decreases while the peak strain increases.Energy evolution follows a pattern of"slow growthfluctuating growthrapid growth,"with the crack initiation stress and its proportion decreasing.CT and SEM analyses reveal that as the impact intensity increases,failure becomes more chaotic,the fracture volume increases,and the fracture mode shifts from interlayer and intergranular to through-layer and trans-granular fractures.These findings provide an experimental basis for soft rock tunnel stability analysis.
