To handle model bias from long-tailed image datasets, most existing studies have proposed to strengthen the focus on tail classes. However, they usually overlook the intricacies of sample learning hardness and feature...
详细信息
PROBLEM Recent years have witnessed the rapid progress of self-supervised language models (LMs)[1],especially large language models (LLMs)[2].LLMs not only achieved state-of-the-art performance on many natural languag...
PROBLEM Recent years have witnessed the rapid progress of self-supervised language models (LMs)[1],especially large language models (LLMs)[2].LLMs not only achieved state-of-the-art performance on many natural language processing tasks,but also captured widespread attention from the public due to their great potential in a variety of real-world applications (***,search engines,writing assistants,etc.)through providing general-purpose intelligent services.A few of the LLMs are becoming foundation models,an analogy to infrastructure,that empower hundreds of downstream applications.
The Sixth-Generation(6G)enhances the Industrial Internet of Things(IIoT)communication efficiency and further raises security *** is crucial to construct a post-quantum security communication channel between any pair o...
详细信息
The Sixth-Generation(6G)enhances the Industrial Internet of Things(IIoT)communication efficiency and further raises security *** is crucial to construct a post-quantum security communication channel between any pair of industrial *** work shows that two legitimate devices can directly extract symmetrical secret keys in information-theoretic secure by measuring their common wireless ***,existing schemes may cause a high bit mismatch rate in IIoT with high *** addition,the physical layer key extraction scheme widely uses passive attack assumptions,which also contradicts the high-security requirements of *** analyzing and modeling IIoT systems and channels,we propose an Adaptive and Robust Secret Key Extraction scheme(ARSKE)from high noise wireless channels in 6G-enabled *** eliminate the non-reciprocity of the wireless channel,we design a smoothing method as the preprocessing ***,we propose a Robust Secure Reconciliation technique that can effectively resist active attacks by jointly designing the information reconciliation and privacy amplification *** real-world experiments are conducted to test the effectiveness and robustness of our scheme.
In airfoil numerical simulation, the mesh quality has an important influence on the accuracy and error of numerical simulation. The existing mesh quality evaluation requires a lot of manual interaction, which greatly ...
详细信息
The person identification task aims to generate robust human representation embeddings. Traditional methods have achieved competitive results, but they face occlusion challenges, making it difficult to distinguish bet...
详细信息
In situ temperature monitoring has become extremely imperative in high-temperature harsh environments and polymer-derived ceramics(PDCs)as sensing materials have attracted great ***,the stability and oxidation/corrosi...
详细信息
In situ temperature monitoring has become extremely imperative in high-temperature harsh environments and polymer-derived ceramics(PDCs)as sensing materials have attracted great ***,the stability and oxidation/corrosion resistance of PDCs cannot be simultaneously achieved at the moment,limiting their practical ***,polymer-derived SiAlBCN ceramics were synthesized via polymer conversion method under different pyrolysis *** microstructure evolution,high temperature sensing properties,and stability were investigated in *** results show that the amorphous SiAlBCN phase grows more orderly and the size of the free carbon phase enlarges with the increasing *** defect concentration displays a decreasing ***,the SiAlBCN ceramics as sensing materials exhibit a good temperature-resistance property from roo temperature to 1100℃.The fabricated SiAlBCN temperature sensor possesses excellent stability,repeatability,and ***,SiAlBCN ceramics exhibit distinguished oxidation/corrosion resistance after 100 h treatment at 1200℃in a water/oxygen environment,which is attributed to their low corrosive rate constant(0.57 mg/(cm^(2)·h))and oxidative rate constant(3.43 mg^(2)/(cm^(4)·h)).Therefore,polymer-derived SiAlBCN ceramics as sensing materials,which possess outstanding stability and oxidation/corrosion resistance,have great potential for in-situ monitoring of extreme environmental temperatures in the future.
Mesh generation is a crucial step in numerical simulations, significantly impacting simulation accuracy and efficiency. However, generating meshes remains time-consuming and requires expensive computational resources....
详细信息
The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing dee...
详细信息
The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.
Global illumination(GI)plays a crucial role in rendering realistic results for virtual exhibitions,such as virtual car *** scenarios usually include all-frequency bidirectional reflectance distribution functions(BRDFs...
详细信息
Global illumination(GI)plays a crucial role in rendering realistic results for virtual exhibitions,such as virtual car *** scenarios usually include all-frequency bidirectional reflectance distribution functions(BRDFs),although their geometries and light configurations may be *** allfrequency BRDFs in real time remains challenging due to the complex light *** approaches,including precomputed radiance transfer,light probes,and the most recent path-tracing-based approaches(ReSTIR PT),cannot satisfy both quality and performance requirements ***,we propose a practical hybrid global illumination approach that combines ray tracing and cached GI by caching the incoming radiance with *** approach can produce results close to those of ofline renderers at the cost of only approximately 17 ms at runtime and is robust over all-frequency *** approach is designed for applications involving static lighting and geometries,such as virtual exhibitions.
Humans are experiencing the inclusion of artificial agents in their lives,such as unmanned vehicles,service robots,voice assistants,and intelligent medical *** the artificial agents cannot align with social values or ...
详细信息
Humans are experiencing the inclusion of artificial agents in their lives,such as unmanned vehicles,service robots,voice assistants,and intelligent medical *** the artificial agents cannot align with social values or make ethical decisions,they may not meet the expectations of ***,an ethical decision-making framework is constructed by rule-based or statistical *** this paper,we propose an ethical decision-making framework based on incremental ILP(Inductive Logic Programming),which can overcome the brittleness of rule-based approaches and little interpretability of statistical *** the current incremental ILP makes it difficult to solve conflicts,we propose a novel ethical decision-making framework considering conflicts in this paper,which adopts our proposed incremental ILP *** framework consists of two processes:the learning process and the deduction *** first process records bottom clauses with their score functions and learns rules guided by the entailment and the score *** second process obtains an ethical decision based on the *** an ethical scenario about chatbots for teenagers’mental health,we verify that our framework can learn ethical rules and make ethical ***,we extract incremental ILP from the framework and compare it with the state-of-the-art ILP systems based on ASP(Answer Set Programming)focusing on conflict *** results of comparisons show that our proposed system can generate better-quality rules than most other systems.
暂无评论