Morality in dialogue systems has raised great attention in research recently. A moral dialogue system could better connect users and enhance conversation engagement by gaining users' trust. In this paper, we propose a framework, MoralDial to train and evaluate moral dialogue systems. In our framework, we first explore the communication mechanisms of morality and resolve expressed morality into four sub-modules. The sub-modules indicate the roadmap for building a moral dialogue system. Based on that, we design a simple yet effective method: constructing moral discussions from Rules of Thumb (RoTs) between simulated specific users and the dialogue system. The constructed discussion consists of expressing, explaining, and revising the moral views in dialogue exchanges, which makes conversational models learn morality well in a natural manner. Furthermore, we propose a novel evaluation method in the framework. We evaluate the multiple aspects of morality by judging the relation between dialogue responses and RoTs in discussions, where the multifaceted nature of morality is particularly considered. Automatic and manual experiments demonstrate that our framework is promising to train and evaluate moral dialogue systems.

磁共振图像（MRI）中的脑肿瘤分割（BTS）对于脑肿瘤诊断，癌症管理和研究目的至关重要。随着十年小型挑战的巨大成功以及CNN和Transformer算法的进步，已经提出了许多出色的BTS模型来解决BTS在不同技术方面的困难。但是，现有研究几乎没有考虑如何以合理的方式融合多模式图像。在本文中，我们利用了放射科医生如何从多种MRI模态诊断脑肿瘤的临床知识，并提出了一种称为CKD-TRANSBTS的临床知识驱动的脑肿瘤分割模型。我们没有直接串联所有模式，而是通过根据MRI的成像原理将输入方式分为两组来重新组织输入方式。具有拟议模态相关的跨意义块（MCCA）的双支支混合式编码器旨在提取多模式图像特征。所提出的模型以局部特征表示能力的能力来继承来自变压器和CNN的强度，以提供精确的病变边界和3D体积图像的远程特征提取。为了弥合变压器和CNN功能之间的间隙，我们提出了解码器中的反式和CNN功能校准块（TCFC）。我们将提出的模型与五个基于CNN的模型和六个基于Transformer的模型在Brats 2021挑战数据集上进行了比较。广泛的实验表明，与所有竞争对手相比，所提出的模型可实现最先进的脑肿瘤分割性能。

联合学习（FL）是一项新兴技术，可在保持数据分布和私密的同时向多个客户培训机器学习模型。根据参与的客户和模型培训量表，可以将联合学习分为两种类型：跨设备FL，客户通常是移动设备，客户编号可以达到数百万的规模；客户是组织或公司，并且客户编号通常很小（例如，一百之内）。尽管现有研究主要集中于跨设备FL，但本文旨在提供跨索洛FL的概述。更具体地说，我们首先讨论了交叉Silo FL的应用，并概述了其主要挑战。然后，我们通过关注与跨设备FL的联系和差异，对Cross-Silo FL挑战的现有方法进行系统的概述。最后，我们讨论了未来的方向和开放问题，值得社区的研究工作。

多ARM强盗（MAB）是一种经典的在线学习框架，可以研究在不确定的环境中的顺序决策。然而，MAB框架忽略了决策者不能直接采取行动（例如，拉臂）的情况。在许多应用中，这是一种实际重要的场景，例如频谱共享，众脉和边缘计算。在这些申请中，决策者将激励其他自私的代理商进行预期的行动（即，在决策者代表武器上撤销）。本文在此方案中建立了激励的在线学习（IOL）框架。设计IOL框架的关键挑战是未知环境学习和非对称信息启示的紧密耦合。为了解决这个问题，我们基于该特殊的拉格朗日功能，我们提出了一种对IOL框架的社会最优机制。我们的机制满足各种理想的属性，如代理公平，激励兼容性和自愿参与。它达到了与需要额外信息的最先进的基准相同的渐近性能。我们的分析还推出了IOL框架中人群的力量：更大的代理人群使我们的机制能够更接近社会绩效的理论上限。数值结果表明了我们在大型边缘计算中的机制的优点。

联合学习（FL）算法通常在每个圆数（部分参与）大并且服务器的通信带宽有限时对每个轮子（部分参与）进行分数。近期对FL的收敛分析的作品专注于无偏见的客户采样，例如，随机均匀地采样，由于高度的系统异质性和统计异质性而均匀地采样。本文旨在设计一种自适应客户采样算法，可以解决系统和统计异质性，以最小化壁时钟收敛时间。我们获得了具有任意客户端采样概率的流动算法的新的遗传融合。基于界限，我们分析了建立了总学习时间和采样概率之间的关系，这导致了用于训练时间最小化的非凸优化问题。我们设计一种高效的算法来学习收敛绑定中未知参数，并开发低复杂性算法以大致解决非凸面问题。硬件原型和仿真的实验结果表明，与几个基线采样方案相比，我们所提出的采样方案显着降低了收敛时间。值得注意的是，我们的硬件原型的方案比均匀的采样基线花费73％，以达到相同的目标损失。

自动视觉解对我们多样化和开放的世界需要计算机视觉模型，以概括为特定任务的最小定制，类似于人类视力。计算机视觉基础型号培训，培训多样化，大型数据集，可以适应各种下游任务，对该任务来解决现实世界计算机视觉应用而言至关重要。虽然现有的视觉基础模型如剪辑，对齐和吴道2.0主要集中在映射图像和文本表示到跨模型共享表示，我们介绍了一台新的计算机视觉基础模型，佛罗伦萨，扩大粗糙的表示（现场）到精细（对象），从静态（图像）到动态（视频），以及从RGB到多个模态（标题，深度）。通过从Web级图像文本数据中纳入通用视觉语言表示，我们的佛罗伦萨模型可以很容易地适应各种计算机视觉任务，例如分类，检索，对象检测，VQA，图像标题，视频检索和动作识别。此外，佛罗伦萨在许多类型的转移学习中表现出出色的表现：全面采样的微调，线性探测，几次射击传输和用于新颖图像和物体的零拍摄传输。所有这些属性对于我们的视觉基础模型至关重要，以提供通用视觉任务。佛罗伦萨实现了新的最先进的导致44个代表性基准，例如Imagenet-1K零射击分类，最高1精度为83.74，最高5个精度为97.18，62.4地图上的Coco微调， 80.36在VQA上，动力学-600上的87.8。

Generalizability to unseen forgery types is crucial for face forgery detectors. Recent works have made significant progress in terms of generalization by synthetic forgery data augmentation. In this work, we explore another path for improving the generalization. Our goal is to reduce the features that are easy to learn in the training phase, so as to reduce the risk of overfitting on specific forgery types. Specifically, in our method, a teacher network takes as input the face images and generates an attention map of the deep features by a diverse multihead attention ViT. The attention map is used to guide a student network to focus on the low-attended features by reducing the highly-attended deep features. A deep feature mixup strategy is also proposed to synthesize forgeries in the feature domain. Experiments demonstrate that, without data augmentation, our method is able to achieve promising performances on unseen forgeries and highly compressed data.

In this work, we investigate improving the generalizability of GAN-generated image detectors by performing data augmentation in the fingerprint domain. Specifically, we first separate the fingerprints and contents of the GAN-generated images using an autoencoder based GAN fingerprint extractor, followed by random perturbations of the fingerprints. Then the original fingerprints are substituted with the perturbed fingerprints and added to the original contents, to produce images that are visually invariant but with distinct fingerprints. The perturbed images can successfully imitate images generated by different GANs to improve the generalization of the detectors, which is demonstrated by the spectra visualization. To our knowledge, we are the first to conduct data augmentation in the fingerprint domain. Our work explores a novel prospect that is distinct from previous works on spatial and frequency domain augmentation. Extensive cross-GAN experiments demonstrate the effectiveness of our method compared to the state-of-the-art methods in detecting fake images generated by unknown GANs.

We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decodert takes as input two types of queries: (i) generic non-semantic queries and (ii) semantic queries induced from text inputs, to decode different pixel-level and token-level outputs in the same semantic space. With such a novel design, X-Decoder is the first work that provides a unified way to support all types of image segmentation and a variety of vision-language (VL) tasks. Further, our design enables seamless interactions across tasks at different granularities and brings mutual benefits by learning a common and rich pixel-level visual-semantic understanding space, without any pseudo-labeling. After pretraining on a mixed set of a limited amount of segmentation data and millions of image-text pairs, X-Decoder exhibits strong transferability to a wide range of downstream tasks in both zero-shot and finetuning settings. Notably, it achieves (1) state-of-the-art results on open-vocabulary segmentation and referring segmentation on eight datasets; (2) better or competitive finetuned performance to other generalist and specialist models on segmentation and VL tasks; and (3) flexibility for efficient finetuning and novel task composition (e.g., referring captioning and image editing). Code, demo, video, and visualization are available at https://x-decoder-vl.github.io.

Developing autonomous vehicles (AVs) helps improve the road safety and traffic efficiency of intelligent transportation systems (ITS). Accurately predicting the trajectories of traffic participants is essential to the decision-making and motion planning of AVs in interactive scenarios. Recently, learning-based trajectory predictors have shown state-of-the-art performance in highway or urban areas. However, most existing learning-based models trained with fixed datasets may perform poorly in continuously changing scenarios. Specifically, they may not perform well in learned scenarios after learning the new one. This phenomenon is called "catastrophic forgetting". Few studies investigate trajectory predictions in continuous scenarios, where catastrophic forgetting may happen. To handle this problem, first, a novel continual learning (CL) approach for vehicle trajectory prediction is proposed in this paper. Then, inspired by brain science, a dynamic memory mechanism is developed by utilizing the measurement of traffic divergence between scenarios, which balances the performance and training efficiency of the proposed CL approach. Finally, datasets collected from different locations are used to design continual training and testing methods in experiments. Experimental results show that the proposed approach achieves consistently high prediction accuracy in continuous scenarios without re-training, which mitigates catastrophic forgetting compared to non-CL approaches. The implementation of the proposed approach is publicly available at https://github.com/BIT-Jack/D-GSM