Neural models with an encoder-decoder framework provide a feasible solution to Question Generation (QG). However, after analyzing the model vocabulary we find that current models (both RNN-based and pre-training based) have more than 23\% inflected forms. As a result, the encoder will generate separate embeddings for the inflected forms, leading to a waste of training data and parameters. Even worse, in decoding these models are vulnerable to irrelevant noise and they suffer from high computational costs. In this paper, we propose an approach to enhance the performance of QG by fusing word transformation. Firstly, we identify the inflected forms of words from the input of encoder, and replace them with the root words, letting the encoder pay more attention to the repetitive root words. Secondly, we propose to adapt QG as a combination of the following actions in the encode-decoder framework: generating a question word, copying a word from the source sequence or generating a word transformation type. Such extension can greatly decrease the size of predicted words in the decoder as well as noise. We apply our approach to a typical RNN-based model and \textsc{UniLM} to get the improved versions. We conduct extensive experiments on SQuAD and MS MARCO datasets. The experimental results show that the improved versions can significantly outperform the corresponding baselines in terms of BLEU, ROUGE-L and METEOR as well as time cost.

Automated Feature Engineering (AFE) refers to automatically generate and select optimal feature sets for downstream tasks, which has achieved great success in real-world applications. Current AFE methods mainly focus on improving the effectiveness of the produced features, but ignoring the low-efficiency issue for large-scale deployment. Therefore, in this work, we propose a generic framework to improve the efficiency of AFE. Specifically, we construct the AFE pipeline based on reinforcement learning setting, where each feature is assigned an agent to perform feature transformation \com{and} selection, and the evaluation score of the produced features in downstream tasks serve as the reward to update the policy. We improve the efficiency of AFE in two perspectives. On the one hand, we develop a Feature Pre-Evaluation (FPE) Model to reduce the sample size and feature size that are two main factors on undermining the efficiency of feature evaluation. On the other hand, we devise a two-stage policy training strategy by running FPE on the pre-evaluation task as the initialization of the policy to avoid training policy from scratch. We conduct comprehensive experiments on 36 datasets in terms of both classification and regression tasks. The results show $2.9\%$ higher performance in average and 2x higher computational efficiency comparing to state-of-the-art AFE methods.

随着智能设备产生的数据快速增长以及物联网（IoT）时代的处理需求的指数激增，资源丰富的云中心已被用来应对这些挑战。为了减轻云中心的负担，边缘云计算卸载成为一个有前途的解决方案，因为通过将计算任务从云到边缘设备缩小计算任务可以改善性能和服务质量（QOS），从而缩短了数据源和计算之间的接近度。已经提出了几种Edge-Cloud计算卸载的优化模型，以考虑计算成本和异质通信成本。但是，没有共同考虑几个重要因素，例如任务的异质性，节点之间的负载平衡以及计算任务所产生的利润，这导致了本文提出的PECCO的利润和面向成本的计算。考虑到该模型本质上很难并且优化目标是无可分析的，我们提出了改进的蛾式优化器PECCO-MFI，该pecco-MFI解决了原始的moth-flame优化器的某些缺陷，并将其集成在边缘环境下。在优化边缘云环境下提议的任务卸载模型时，进行了全面的实验，以验证所提出的方法的出色性能。

基于范围视图的LIDAR分割方法由于其直接继承了有效的2D CNN体系结构，因此对实际应用具有吸引力。在文献中，大多数基于范围的方法都遵循每个像素分类范式。最近，在图像分割域中，另一个范式将分割作为面具分类问题，并实现了出色的性能。这提出了一个有趣的问题：掩码分类范式是否可以使基于范围的LIDAR分割受益并获得比每个像素范式对应的更好的性能？为了回答这个问题，我们为基于范围视图的LIDAR语义和全景分段提出了一个统一的面膜分类模型MaskRange。除了新的范式外，我们还提出了一种新型的数据增强方法，以应对过度拟合，上下文依赖和班级不平衡问题。大量实验是在Semantickitti基准测试上进行的。在所有基于范围视图的方法中，我们的面具以$ 66.10 $ MIOU的语义细分和有希望的结果以$ 53.10 $ pq的pq pq in Panoptic细分，以高效的效率达到了最新的性能。我们的代码将发布。

Realizing human-like perception is a challenge in open driving scenarios due to corner cases and visual occlusions. To gather knowledge of rare and occluded instances, federated learning assisted connected autonomous vehicle (FLCAV) has been proposed, which leverages vehicular networks to establish federated deep neural networks (DNNs) from distributed data captured by vehicles and road sensors. Without the need of data aggregation, FLCAV preserves privacy while reducing communication costs compared with conventional centralized learning. However, it is challenging to determine the network resources and road sensor placements for multi-stage training with multi-modal datasets in multi-variant scenarios. This article presents networking and training frameworks for FLCAV perception. Multi-layer graph resource allocation and vehicle-road contrastive sensor placement are proposed to address the network management and sensor deployment problems, respectively. We also develop CarlaFLCAV, a software platform that implements the above system and methods. Experimental results confirm the superiority of the proposed techniques compared with various benchmarks.

在城市环境中面对道路选项问题时，现有的仿制学习方法遭受了低效率和泛化能力。在本文中，我们提出了一种横摆引导的仿制学习方法，以提高端到端自主驾驶范式的道路选择性能，就利用培训样本和对不断变化的环境的适应性而言。具体地，偏航信息由导航图的轨迹提供。我们的端到端架构，偏航引导模仿学习与Resnet34注意（YILRATT），集成了Resnet34主干和注意机制，以获得准确的感知。它不需要高精度地图，并且在给定由消费级GPS接收器提供的偏航信息的情况下实现完全端到端的自主驱动。通过分析注意热图，我们可以揭示决策和场景感知之间的一些因果关系，特别是故障情况是由错误的感知引起的。我们在Carla 0.9.11模拟器中收集专家体验，并改善基准科尔2017和NOCRASH。实验结果表明，伊利拉特比SOTA CILRS的成功率较高26.27％。代码，数据集，基准和实验结果可以在https://github.com/yandong024/yaw-guiding -il.git找到

准确预测短期OD矩阵（即，从各种来源到目的地的乘客流量的分布）是地铁系统中的一个重要任务。由于许多影响因素的不断变化的性质和实时延迟数据收集问题，这是强大的挑战性。最近，已经提出了一些基于学习的基于学习的模型，以便在乘车和高速公路中进行OD矩阵预测。然而，由于其不同的先验知识和上下文设置，这些模型不能充分捕获地铁网络中的站点之间的复杂时空相关性。在本文中，我们提出了一个混合框架多视图Trgru来解决OD Metro Matrix预测。特别是，它使用三个模块来模拟三个流动变化模式：最近的趋势，日常趋势，每周趋势。在每个模块中，基于每个站的嵌入的多视图表示被构造并馈送到基于变压器的门控复发结构，以通过全球自我注意机制捕获不同站的OD流的动态空间依赖性。在三种大型现实世界地铁数据集上进行了广泛的实验，证明了我们的多视图Trgru在其他竞争对手的优越性。

在集成感测和通信（ISAC）系统中表征传感和通信性能权衡，在基于学习的人类运动识别的应用中具有挑战性。这是因为大型实验数据集和深神经网络的黑盒性质。本文介绍了SDP3，这是一种模拟驱动的性能预测指标和优化器，由SDP3数据模拟器，SDP3性能预测器和SDP3性能优化器组成。具体而言，SDP3数据模拟器在虚拟环境中生成生动的无线传感数据集，SDP3性能预测器预测基于函数回归方法的传感性能，而SDP3性能优化器会在分析上研究传感和通信性能。结果表明，模拟传感数据集在运动识别精度中非常匹配实验数据集。通过利用SDP3，发现可实现的识别准确性和通信吞吐量由通信饱和区组成，感应饱和区和通讯感应的对抗区域，ISAC系统的所需平衡性能位于第三个一。

我们考虑了一类不安的匪徒问题，这些问题在随机优化，增强学习和操作研究中发现了一个广泛的应用领域。我们考虑$ n $独立离散时间马尔可夫流程，每个过程都有两个可能的状态：1和0（“好”和“坏”）。只有在状态1中既有过程又观察到的过程才能得到奖励。目的是最大限度地提高无限视野的预期折扣总和，受到约束，即在每个步骤中只能观察到$ m $ $ $（<n）$。观察是容易出错的：有一个已知的概率，即状态1（0）将被观察为0（1）。从这个人知道，在任何时候$ t $，过程$ i $在状态1中的概率1。可以将结果系统建模为不​​安的多臂强盗问题，具有无数基数的信息状态空间。一般而言，即使是有限状态空间的不安强盗问题也是Pspace-Hard。我们提出了一种新颖的方法，以简化这类不安的土匪的动态编程方程，并开发出一种低复杂性算法，该算法实现了强劲的性能，并且对于带有观察错误的一般不安强盗模型而言，很容易扩展。在某些条件下，我们确定了Whittle指数的存在（索引性）及其与我们的算法的等效性。当这些条件不满足时，我们通过数值实验显示了算法在一般参数空间中的近乎最佳性能。最后，从理论上讲，我们证明了我们算法对于均匀系统的最佳性。

Few Shot Instance Segmentation (FSIS) requires models to detect and segment novel classes with limited several support examples. In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework. Our key insights are two folds: Firstly, with the aid of support masks, we can generate dynamic class centers more appropriately to re-weight query features. Secondly, we find that support object queries have already encoded key factors after base training. In this way, the query features can be enhanced twice from two aspects, i.e., feature-level and instance-level. In particular, we firstly design a mask-based dynamic weighting module to enhance support features and then propose to link object queries for better calibration via cross-attention. After the above steps, the novel classes can be improved significantly over our strong baseline. Additionally, our new framework can be easily extended to incremental FSIS with minor modification. When benchmarking results on the COCO dataset for FSIS, gFSIS, and iFSIS settings, our method achieves a competitive performance compared to existing approaches across different shots, e.g., we boost nAP by noticeable +8.2/+9.4 over the current state-of-the-art FSIS method for 10/30-shot. We further demonstrate the superiority of our approach on Few Shot Object Detection. Code and model will be available.