Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

关于点击率（CTR）预测的最新研究通过对更长的用户行为序列进行建模，已达到新的水平。除其他外，两阶段的方法是用于工业应用的最先进的解决方案（SOTA）。两阶段方法首先训练检索模型，以事先截断长行为序列，然后使用截短序列训练CTR模型。但是，检索模型和CTR模型是分别训练的。因此，CTR模型中检索到的子序列不准确，它降低了最终性能。在本文中，我们提出了一个端到端范式来建模长行为序列，与现有模型相比，该序列能够实现卓越的性能以及出色的成本效益。我们的贡献是三倍：首先，我们提出了一个名为ETA-NET的基于哈希的有效目标（TA）网络，以基于低成本的位置操作来启用端到端的用户行为检索。提出的ETA-NET可以通过顺序数据建模的数量级来降低标准TA的复杂性。其次，我们建议将通用系统体系结构作为一种可行的解决方案，用于在工业系统上部署ETA-NET。特别是，与SOTA两阶段方法相比，ETA-NET已部署在TAOBAO的推荐系统上，并在CTR上带来了1.8％的升降机和3.1％的升降机（GMV）。第三，我们在离线数据集和在线A/B测试上进行了广泛的实验。结果证明，在CTR预测性能和在线成本效益方面，所提出的模型大大优于现有的CTR模型。 ETA-NET现在为TAOBAO的主要流量提供服务，每天为数亿用户提供服务。

在本文中，我们介绍了OpenMedia，这是一个开源工具箱库，其中包含在异质人工智能（AI）计算平台下用于医学图像分析的丰富深度学习方法。各种医学图像分析方法，包括2D $/$ 3D医疗图像分类，细分，本地化和检测，已与Pytorch和$/$或Mindspore实现在异质NVIDIA和HUAWEI ASCEND ASCEND Computing系统下包含在工具箱中。据我们所知，OpenMedia是第一个提供Pytorch和Mindsp的开源算法库

知识蒸馏（KD）将知识从高容量的教师网络转移到加强较小的学生。现有方法着重于发掘知识的提示，并将整个知识转移给学生。但是，由于知识在不同的学习阶段显示出对学生的价值观，因此出现了知识冗余。在本文中，我们提出了知识冷凝蒸馏（KCD）。具体而言，每个样本上的知识价值是动态估计的，基于期望最大化（EM）框架的迭代性凝结，从老师那里划定了一个紧凑的知识，以指导学生学习。我们的方法很容易建立在现成的KD方法之上，没有额外的培训参数和可忽略不计的计算开销。因此，它为KD提出了一种新的观点，在该观点中，积极地识别教师知识的学生可以学会更有效，有效地学习。对标准基准测试的实验表明，提出的KCD可以很好地提高学生模型的性能，甚至更高的蒸馏效率。代码可在https://github.com/dzy3/kcd上找到。

我们提出了一种降低概率图形模型中普遍存在的吉布斯（Boltzmann）分布的分区功能（标准化常数）的计算复杂性的新方法。 Gibbs分布的实际应用的主要障碍是需要估计其分区功能。在解决该问题的情况下，本领域的状态是多级算法，其包括冷却时间表，以及时间表的每个步骤中的平均估计器。虽然这些算法中的冷却时间表是自适应的，但平均估计计算使用MCMC作为黑盒以绘制近似样本。我们开发了一种双重自适应方法，将自适应冷却时间与自适应MCMC平均估计器相结合，其数量的马尔可夫链步骤动态地适应下面的链条。通过严格的理论分析，我们证明了我们的方法在几个因素中优于最新的技术算法：（1）我们方法的计算复杂性较小; （2）我们的方法对混合时间的松散界限敏感，这些算法中的固有组成部分; （3）我们方法获得的改进在高精度估计的最具挑战性方案中特别显着。我们展示了我们在经典因素图中运行的实验中的方法的优势，例如投票模型和ising模型。

我们为图像去噪提供了一个名为自我验证的新正规化。使用网络以前的深度图像而不是传统的预定义先决义的阵列制定了这种正则化。具体而言，我们将网络的输出视为“先前”，我们在“重新注册”之后再次欺骗。再次去噪图像与其之前的比较可以解释为网络的去噪能力的自我验证。我们证明自我验证鼓励网络捕获恢复图像所需的低级图像统计数据。基于这种自我验证正规化，我们进一步表明，即使它没有看到任何清洁图像，网络也可以学习去代标。这种学习策略是自我监督的，我们将其称为自我验证图像去噪（SVID）。 SVID可以被视为基于学习的方法和传统的基于模型的去噪方法的混合，其中使用网络的输出自适应地配制正则化。我们仅使用观察到损坏的数据显示SVID对各种去噪任务的应用。它可以实现接近监督CNN的去噪性能。

联邦元学习（FML）已成为应对当今边缘学习竞技场中的数据限制和异质性挑战的承诺范式。然而，其性能通常受到缓慢的收敛性和相应的低通信效率的限制。此外，由于可用的无线电频谱和物联网设备的能量容量通常不足，因此在在实际无线网络中部署FML时，控制资源分配和能量消耗是至关重要的。为了克服挑战，在本文中，我们严格地分析了每个设备对每轮全球损失减少的贡献，并使用非统一的设备选择方案开发FML算法（称为Nufm）以加速收敛。之后，我们制定了集成NuFM在多通道无线系统中的资源分配问题，共同提高收敛速率并最小化壁钟时间以及能量成本。通过逐步解构原始问题，我们设计了一个联合设备选择和资源分配策略，以解决理论保证问题。此外，我们表明Nufm的计算复杂性可以通过$ O（d ^ 2）$至$ o（d）$（使用模型维度$ d $）通过组合两个一阶近似技术来降低。广泛的仿真结果表明，与现有基线相比，所提出的方法的有效性和优越性。

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.

Benefiting from the intrinsic supervision information exploitation capability, contrastive learning has achieved promising performance in the field of deep graph clustering recently. However, we observe that two drawbacks of the positive and negative sample construction mechanisms limit the performance of existing algorithms from further improvement. 1) The quality of positive samples heavily depends on the carefully designed data augmentations, while inappropriate data augmentations would easily lead to the semantic drift and indiscriminative positive samples. 2) The constructed negative samples are not reliable for ignoring important clustering information. To solve these problems, we propose a Cluster-guided Contrastive deep Graph Clustering network (CCGC) by mining the intrinsic supervision information in the high-confidence clustering results. Specifically, instead of conducting complex node or edge perturbation, we construct two views of the graph by designing special Siamese encoders whose weights are not shared between the sibling sub-networks. Then, guided by the high-confidence clustering information, we carefully select and construct the positive samples from the same high-confidence cluster in two views. Moreover, to construct semantic meaningful negative sample pairs, we regard the centers of different high-confidence clusters as negative samples, thus improving the discriminative capability and reliability of the constructed sample pairs. Lastly, we design an objective function to pull close the samples from the same cluster while pushing away those from other clusters by maximizing and minimizing the cross-view cosine similarity between positive and negative samples. Extensive experimental results on six datasets demonstrate the effectiveness of CCGC compared with the existing state-of-the-art algorithms.

In robust Markov decision processes (MDPs), the uncertainty in the transition kernel is addressed by finding a policy that optimizes the worst-case performance over an uncertainty set of MDPs. While much of the literature has focused on discounted MDPs, robust average-reward MDPs remain largely unexplored. In this paper, we focus on robust average-reward MDPs, where the goal is to find a policy that optimizes the worst-case average reward over an uncertainty set. We first take an approach that approximates average-reward MDPs using discounted MDPs. We prove that the robust discounted value function converges to the robust average-reward as the discount factor $\gamma$ goes to $1$, and moreover, when $\gamma$ is large, any optimal policy of the robust discounted MDP is also an optimal policy of the robust average-reward. We further design a robust dynamic programming approach, and theoretically characterize its convergence to the optimum. Then, we investigate robust average-reward MDPs directly without using discounted MDPs as an intermediate step. We derive the robust Bellman equation for robust average-reward MDPs, prove that the optimal policy can be derived from its solution, and further design a robust relative value iteration algorithm that provably finds its solution, or equivalently, the optimal robust policy.