Structured Complex Task Decomposition (SCTD) is the problem of breaking down a complex real-world task (such as planning a wedding) into a directed acyclic graph over individual steps that contribute to achieving the task, with edges specifying temporal dependencies between them. SCTD is an important component of assistive planning tools, and a challenge for commonsense reasoning systems. We probe how accurately SCTD can be done with the knowledge extracted from Large Language Models (LLMs). We introduce a high-quality human-annotated dataset for this problem and novel metrics to fairly assess performance of LLMs against several baselines. Our experiments reveal that LLMs are able to decompose complex tasks into individual steps effectively, with a relative improvement of 15% to 280% over the best baseline. We also propose a number of approaches to further improve their performance, with a relative improvement of 7% to 37% over the base model. However, we find that LLMs still struggle to predict pairwise temporal dependencies, which reveals a gap in their understanding of complex tasks.
相關內容
Controlling the False Discovery Rate (FDR) in a variable selection procedure is critical for reproducible discoveries, and it has been extensively studied in sparse linear models. However, it remains largely open in scenarios where the sparsity constraint is not directly imposed on the parameters but on a linear transformation of the parameters to be estimated. Examples of such scenarios include total variations, wavelet transforms, fused LASSO, and trend filtering. In this paper, we propose a data-adaptive FDR control method, called the Split Knockoff method, for this transformational sparsity setting. The proposed method exploits both variable and data splitting. The linear transformation constraint is relaxed to its Euclidean proximity in a lifted parameter space, which yields an orthogonal design that enables the orthogonal Split Knockoff construction. To overcome the challenge that exchangeability fails due to the heterogeneous noise brought by the transformation, new inverse supermartingale structures are developed via data splitting for provable FDR control without sacrificing power. Simulation experiments demonstrate that the proposed methodology achieves the desired FDR and power. We also provide an application to Alzheimer's Disease study, where atrophy brain regions and their abnormal connections can be discovered based on a structural Magnetic Resonance Imaging dataset (ADNI).
Submarine cables constitute the backbone of the Internet. However, these critical infrastructure components are vulnerable to several natural and man-made threats, and during failures, are difficult to repair in their remote oceanic environments. In spite of their crucial role, we have a limited understanding of the impact of submarine cable failures on global connectivity, particularly on the higher layers of the Internet. In this paper, we present Nautilus, a framework for cross-layer cartography of submarine cables and IP links. Using a corpus of public datasets and Internet cartographic techniques, Nautilus identifies IP links that are likely traversing submarine cables and maps them to one or more potential cables. Nautilus also gives each IP to cable assignment a prediction score that reflects the confidence in the mapping. Nautilus generates a mapping for 3.05 million and 1.43 million IPv4 and IPv6 links respectively, covering 91% of all active cables. In the absence of ground truth data, we validate Nautilus mapping using three techniques: analyzing past cable failures, using targeted traceroute measurements, and comparing with public network maps of two operators.
In the area of fewshot anomaly detection (FSAD), efficient visual feature plays an essential role in memory bank M-based methods. However, these methods do not account for the relationship between the visual feature and its rotated visual feature, drastically limiting the anomaly detection performance. To push the limits, we reveal that rotation-invariant feature property has a significant impact in industrial-based FSAD. Specifically, we utilize graph representation in FSAD and provide a novel visual isometric invariant feature (VIIF) as anomaly measurement feature. As a result, VIIF can robustly improve the anomaly discriminating ability and can further reduce the size of redundant features stored in M by a large amount. Besides, we provide a novel model GraphCore via VIIFs that can fast implement unsupervised FSAD training and can improve the performance of anomaly detection. A comprehensive evaluation is provided for comparing GraphCore and other SOTA anomaly detection models under our proposed fewshot anomaly detection setting, which shows GraphCore can increase average AUC by 5.8%, 4.1%, 3.4%, and 1.6% on MVTec AD and by 25.5%, 22.0%, 16.9%, and 14.1% on MPDD for 1, 2, 4, and 8-shot cases, respectively.
Saturation-Aware Angular Velocity Estimation: Extending the Robustness of SLAM to Aggressive Motions
We propose a novel angular velocity estimation method to increase the robustness of Simultaneous Localization And Mapping (SLAM) algorithms against gyroscope saturations induced by aggressive motions. Field robotics expose robots to various hazards, including steep terrains, landslides, and staircases, where substantial accelerations and angular velocities can occur if the robot loses stability and tumbles. These extreme motions can saturate sensor measurements, especially gyroscopes, which are the first sensors to become inoperative. While the structural integrity of the robot is at risk, the resilience of the SLAM framework is oftentimes given little consideration. Consequently, even if the robot is physically capable of continuing the mission, its operation will be compromised due to a corrupted representation of the world. Regarding this problem, we propose a way to estimate the angular velocity using accelerometers during extreme rotations caused by tumbling. We show that our method reduces the median localization error by 71.5 % in translation and 65.5 % in rotation and reduces the number of SLAM failures by 73.3 % on the collected data. We also propose the Tumbling-Induced Gyroscope Saturation (TIGS) dataset, which consists of outdoor experiments recording the motion of a lidar subject to angular velocities four times higher than other available datasets. The dataset is available online at //github.com/norlab-ulaval/Norlab_wiki/wiki/TIGS-Dataset.
Purpose: Technology plays a pivotal role in shaping the fate of organizations, both positively and negatively. One of its detrimental consequences is the emergence of "Technostress," a form of destructive stress. This paper investigates the impact of technostress on Perceived Organizational Commitment (POC) through the lens of individual innovation. The objective is to provide valuable insights for organizational managers, enabling them to effectively mitigate the adverse effects of technostress within their teams. Design/Methodology/Approach: This study utilized a questionnaire survey conducted within an Engineering Consulting Company in Iran, with 147 individuals participating, selected according to Morgan's table. Findings: The research findings revealed three crucial insights: (1) Technostress significantly and negatively influences both POC and individual innovation. (2) Individual innovation positively and significantly impacts POC. (3) Individual innovation acts as a mediator between technostress and POC, alleviating the negative impact of technostress on organizational commitment. Research Implications: The study underscores the importance for managers to proactively address technostress-related challenges and promote individual innovation within their organizations. These efforts are vital in enhancing organizational commitment among employees. Originality/Value: This research makes a significant contribution to the field by illuminating the mediating role of individual innovation in the relationship between technostress and perceived organizational commitment. Given the close association of employees in engineering organizations with technology, this study sheds light on the specific challenges faced by this sector, thereby enhancing our understanding of technostress effects in the workplace.
Recent years have witnessed the rapid development and wide adoption of immersive head-mounted devices, such as HTC VIVE, Oculus Rift, and Microsoft HoloLens. These immersive devices have the potential to significantly extend the methodology of urban visual analytics by providing critical 3D context information and creating a sense of presence. In this paper, we propose an theoretical model to characterize the visualizations in immersive urban analytics. Further more, based on our comprehensive and concise model, we contribute a typology of combination methods of 2D and 3D visualizations that distinguish between linked views, embedded views, and mixed views. We also propose a supporting guideline to assist users in selecting a proper view under certain circumstances by considering visual geometry and spatial distribution of the 2D and 3D visualizations. Finally, based on existing works, possible future research opportunities are explored and discussed.
Knowledge plays a critical role in artificial intelligence. Recently, the extensive success of pre-trained language models (PLMs) has raised significant attention about how knowledge can be acquired, maintained, updated and used by language models. Despite the enormous amount of related studies, there still lacks a unified view of how knowledge circulates within language models throughout the learning, tuning, and application processes, which may prevent us from further understanding the connections between current progress or realizing existing limitations. In this survey, we revisit PLMs as knowledge-based systems by dividing the life circle of knowledge in PLMs into five critical periods, and investigating how knowledge circulates when it is built, maintained and used. To this end, we systematically review existing studies of each period of the knowledge life cycle, summarize the main challenges and current limitations, and discuss future directions.
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question answering or machine translation). However, it builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. Moreover, it is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime. The first goal of this thesis is to characterize the different forms this shift can take in the context of natural language processing, and propose benchmarks and evaluation metrics to measure its effect on current deep learning architectures. We then proceed to take steps to mitigate the effect of distributional shift on NLP models. To this end, we develop methods based on parametric reformulations of the distributionally robust optimization framework. Empirically, we demonstrate that these approaches yield more robust models as demonstrated on a selection of realistic problems. In the third and final part of this thesis, we explore ways of efficiently adapting existing models to new domains or tasks. Our contribution to this topic takes inspiration from information geometry to derive a new gradient update rule which alleviate catastrophic forgetting issues during adaptation.
Graph Neural Networks (GNNs) have been studied from the lens of expressive power and generalization. However, their optimization properties are less well understood. We take the first step towards analyzing GNN training by studying the gradient dynamics of GNNs. First, we analyze linearized GNNs and prove that despite the non-convexity of training, convergence to a global minimum at a linear rate is guaranteed under mild assumptions that we validate on real-world graphs. Second, we study what may affect the GNNs' training speed. Our results show that the training of GNNs is implicitly accelerated by skip connections, more depth, and/or a good label distribution. Empirical results confirm that our theoretical results for linearized GNNs align with the training behavior of nonlinear GNNs. Our results provide the first theoretical support for the success of GNNs with skip connections in terms of optimization, and suggest that deep GNNs with skip connections would be promising in practice.
Deep Convolutional Neural Networks (CNNs) are a special type of Neural Networks, which have shown state-of-the-art results on various competitive benchmarks. The powerful learning ability of deep CNN is largely achieved with the use of multiple non-linear feature extraction stages that can automatically learn hierarchical representation from the data. Availability of a large amount of data and improvements in the hardware processing units have accelerated the research in CNNs and recently very interesting deep CNN architectures are reported. The recent race in deep CNN architectures for achieving high performance on the challenging benchmarks has shown that the innovative architectural ideas, as well as parameter optimization, can improve the CNN performance on various vision-related tasks. In this regard, different ideas in the CNN design have been explored such as use of different activation and loss functions, parameter optimization, regularization, and restructuring of processing units. However, the major improvement in representational capacity is achieved by the restructuring of the processing units. Especially, the idea of using a block as a structural unit instead of a layer is gaining substantial appreciation. This survey thus focuses on the intrinsic taxonomy present in the recently reported CNN architectures and consequently, classifies the recent innovations in CNN architectures into seven different categories. These seven categories are based on spatial exploitation, depth, multi-path, width, feature map exploitation, channel boosting and attention. Additionally, it covers the elementary understanding of the CNN components and sheds light on the current challenges and applications of CNNs.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191