Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate answers. Retrievers and readers are usually modeled separately, which necessitates a cumbersome implementation and is hard to train and adapt in an end-to-end fashion. In this paper, we revisit this design and eschew the separate architecture and training in favor of a single Transformer that performs Retrieval as Attention (ReAtt), and end-to-end training solely based on supervision from the end QA task. We demonstrate for the first time that a single model trained end-to-end can achieve both competitive retrieval and QA performance, matching or slightly outperforming state-of-the-art separately trained retrievers and readers. Moreover, end-to-end adaptation significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings, making our model a simple and adaptable solution for knowledge-intensive tasks. Code and models are available at https://github.com/jzbjyb/ReAtt.

This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage translation paradigm called Hybrid Regression Translation (HRT) to combine the advantages of autoregressive and non-autoregressive translation. Specifically, HRT first autoregressively generates a discontinuous sequence (e.g., make a prediction every $k$ tokens, $k>1$) and then fills in all previously skipped tokens at once in a non-autoregressive manner. Thus, we can easily trade off the translation quality and speed by adjusting $k$. In addition, by integrating other modeling techniques (e.g., sequence-level knowledge distillation and deep-encoder-shallow-decoder layer allocation strategy) and a mass of engineering efforts, HRT improves 80\% inference speed and achieves equivalent translation performance with the same-capacity AT counterpart. Our fastest system reaches 6k+ words/second on the GPU latency setting, estimated to be about 3.1x faster than the last year's winner.

Arbitrary style transfer (AST) transfers arbitrary artistic styles onto content images. Despite the recent rapid progress, existing AST methods are either incapable or too slow to run at ultra-resolutions (e.g., 4K) with limited resources, which heavily hinders their further applications. In this paper, we tackle this dilemma by learning a straightforward and lightweight model, dubbed MicroAST. The key insight is to completely abandon the use of cumbersome pre-trained Deep Convolutional Neural Networks (e.g., VGG) at inference. Instead, we design two micro encoders (content and style encoders) and one micro decoder for style transfer. The content encoder aims at extracting the main structure of the content image. The style encoder, coupled with a modulator, encodes the style image into learnable dual-modulation signals that modulate both intermediate features and convolutional filters of the decoder, thus injecting more sophisticated and flexible style signals to guide the stylizations. In addition, to boost the ability of the style encoder to extract more distinct and representative style signals, we also introduce a new style signal contrastive loss in our model. Compared to the state of the art, our MicroAST not only produces visually superior results but also is 5-73 times smaller and 6-18 times faster, for the first time enabling super-fast (about 0.5 seconds) AST at 4K ultra-resolutions. Code is available at https://github.com/EndyWon/MicroAST.

尖峰神经网络（SNN）是第三代人工神经网络，可以在神经形态硬件上实施节能。但是，尖峰的离散传播给坚固且高性能的学习机制带来了重大挑战。大多数现有的作品仅着眼于神经元之间的学习，但忽略了突触之间的影响，从而导致稳健性和准确性丧失。为了解决这个问题，我们通过对突触（APB）（APB）之间的关联可塑性（APB）进行建模，从而提出了一种强大而有效的学习机制。使用提出的APB方法，当其他神经元同时刺激时，同一神经元的突触通过共享因素相互作用。此外，我们提出了一种时空种植和翻转（STCF）方法，以提高网络的概括能力。广泛的实验表明，我们的方法在静态CIFAR-10数据集和神经形态MNIST-DV的最新性能上实现了卓越的性能，通过轻量级卷积网络，CIFAR10-DVS数据集。据我们所知，这是第一次探索突触之间的学习方法和神经形态数据的扩展方法。

事件摄像机在挑战场景中具有巨大的潜力，因为其高度分辨率，高动态范围，低功耗和无运动模糊的优势。但是，基于事件的学习受到不足的概括能力的阻碍。在本文中，我们首先分析不同亮度变化对事件数据的影响。然后，我们提出了两种新颖的增强方法：事件逆转和eventdrift。通过将事件逆转和漂移到时空或极性域中的相应位置，提出的方法会生成受不同亮度变化影响的样品，从而改善了基于事件的学习的鲁棒性，并导致更好的概括。N-CARS，N-Caltech101和CIFAR10-DVS数据集的广泛实验表明，我们的方法是一般且非常有效的。

现代有效的卷积神经网络（CNN）始终使用可分开的卷积（DSC）和神经体系结构搜索（NAS）来减少参数数量和计算复杂性。但是网络的一些固有特征被忽略了。受到可视化功能地图和n $ \ times $ n（n $> $ 1）卷积内核的启发，本文介绍了几种准则，以进一步提高参数效率和推理速度。基于这些准则，我们的参数有效的CNN体​​系结构称为\ textit {vgnetg}，比以前的网络更高的准确性和延迟较低，降低了约30％$ \厚度$ 50％的参数。我们的VGNETG-1.0MP在ImageNet分类数据集上具有0.99万参数的67.7％TOP-1准确性和69.2％的TOP-1精度，而参数为114m。此外，我们证明边缘检测器可以通过用固定的边缘检测核代替N $ \ times $ n内核来代替可学习的深度卷积层来混合特征。我们的VGNETF-1.5MP存档64.4％（ - 3.2％）的TOP-1准确性和66.2％（-1.4％）的TOP-1准确性，具有额外的高斯内核。

在现实世界应用中的深度神经网络（DNN）的成功受益于丰富的预训练模型。然而，回溯预训练模型可以对下游DNN的部署构成显着的特洛伊木马威胁。现有的DNN测试方法主要旨在在对抗性设置中找到错误的角壳行为，但未能发现由强大的木马攻击所制作的后门。观察特洛伊木马网络行为表明，它们不仅由先前的工作所提出的单一受损神经元反射，而且归因于在多个神经元的激活强度和频率中的关键神经路径。这项工作制定了DNN后门测试，并提出了录音机框架。通过少量良性示例的关键神经元的差异模糊，我们识别特洛伊木马路径，特别是临界人，并通过模拟所识别的路径中的关键神经元来产生后门测试示例。广泛的实验表明了追索者的优越性，比现有方法更高的检测性能。通过隐秘的混合和自适应攻击来检测到后门的录音机更好，现有方法无法检测到。此外，我们的实验表明，录音所可能会揭示模型动物园中的模型的潜在潜在的背面。

在本文中，我们介绍了纹理改革器，一个快速和通用的神经基础框架，用于使用用户指定的指导进行交互式纹理传输。挑战在三个方面：1）任务的多样性，2）引导图的简单性，以及3）执行效率。为了解决这些挑战，我们的主要思想是使用由i）全球视图结构对准阶段，ii）局部视图纹理细化阶段和III）的新的前馈多视图和多级合成程序。效果增强阶段用相干结构合成高质量结果，并以粗略的方式进行细纹细节。此外，我们还介绍了一种新颖的无学习视图特定的纹理改革（VSTR）操作，具有新的语义地图指导策略，以实现更准确的语义引导和结构保存的纹理传输。关于各种应用场景的实验结果展示了我们框架的有效性和优越性。并与最先进的交互式纹理转移算法相比，它不仅可以实现更高的质量结果，而且更加显着，也是更快的2-5个数量级。代码可在https://github.com/endywon/texture --reformer中找到。

Among current anchor-based detectors, a positive anchor box will be intuitively assigned to the object that overlaps it the most. The assigned label to each anchor will directly determine the optimization direction of the corresponding prediction box, including the direction of box regression and category prediction. In our practice of crowded object detection, however, the results show that a positive anchor does not always regress toward the object that overlaps it the most when multiple objects overlap. We name it anchor drift. The anchor drift reflects that the anchor-object matching relation, which is determined by the degree of overlap between anchors and objects, is not always optimal. Conflicts between the fixed matching relation and learned experience in the past training process may cause ambiguous predictions and thus raise the false-positive rate. In this paper, a simple but efficient adaptive two-stage anchor assignment (TSAA) method is proposed. It utilizes the final prediction boxes rather than the fixed anchors to calculate the overlap degree with objects to determine which object to regress for each anchor. The participation of the prediction box makes the anchor-object assignment mechanism adaptive. Extensive experiments are conducted on three classic detectors RetinaNet, Faster-RCNN and YOLOv3 on CrowdHuman and COCO to evaluate the effectiveness of TSAA. The results show that TSAA can significantly improve the detectors' performance without additional computational costs or network structure changes.

A key assumption in most existing works on FL algorithms' convergence analysis is that the noise in stochastic first-order information has a finite variance. Although this assumption covers all light-tailed (i.e., sub-exponential) and some heavy-tailed noise distributions (e.g., log-normal, Weibull, and some Pareto distributions), it fails for many fat-tailed noise distributions (i.e., ``heavier-tailed'' with potentially infinite variance) that have been empirically observed in the FL literature. To date, it remains unclear whether one can design convergent algorithms for FL systems that experience fat-tailed noise. This motivates us to fill this gap in this paper by proposing an algorithmic framework called FAT-Clipping (\ul{f}ederated \ul{a}veraging with \ul{t}wo-sided learning rates and \ul{clipping}), which contains two variants: FAT-Clipping per-round (FAT-Clipping-PR) and FAT-Clipping per-iteration (FAT-Clipping-PI). Specifically, for the largest $\alpha \in (1,2]$ such that the fat-tailed noise in FL still has a bounded $\alpha$-moment, we show that both variants achieve $\mathcal{O}((mT)^{\frac{2-\alpha}{\alpha}})$ and $\mathcal{O}((mT)^{\frac{1-\alpha}{3\alpha-2}})$ convergence rates in the strongly-convex and general non-convex settings, respectively, where $m$ and $T$ are the numbers of clients and communication rounds. Moreover, at the expense of more clipping operations compared to FAT-Clipping-PR, FAT-Clipping-PI further enjoys a linear speedup effect with respect to the number of local updates at each client and being lower-bound-matching (i.e., order-optimal). Collectively, our results advance the understanding of designing efficient algorithms for FL systems that exhibit fat-tailed first-order oracle information.