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.

Automatic parsing of human anatomies at instance-level from 3D computed tomography (CT) scans is a prerequisite step for many clinical applications. The presence of pathologies, broken structures or limited field-of-view (FOV) all can make anatomy parsing algorithms vulnerable. In this work, we explore how to exploit and conduct the prosperous detection-then-segmentation paradigm in 3D medical data, and propose a steerable, robust, and efficient computing framework for detection, identification, and segmentation of anatomies in CT scans. Considering complicated shapes, sizes and orientations of anatomies, without lose of generality, we present the nine degrees-of-freedom (9-DoF) pose estimation solution in full 3D space using a novel single-stage, non-hierarchical forward representation. Our whole framework is executed in a steerable manner where any anatomy of interest can be directly retrieved to further boost the inference efficiency. We have validated the proposed method on three medical imaging parsing tasks of ribs, spine, and abdominal organs. For rib parsing, CT scans have been annotated at the rib instance-level for quantitative evaluation, similarly for spine vertebrae and abdominal organs. Extensive experiments on 9-DoF box detection and rib instance segmentation demonstrate the effectiveness of our framework (with the identification rate of 97.0% and the segmentation Dice score of 90.9%) in high efficiency, compared favorably against several strong baselines (e.g., CenterNet, FCOS, and nnU-Net). For spine identification and segmentation, our method achieves a new state-of-the-art result on the public CTSpine1K dataset. Last, we report highly competitive results in multi-organ segmentation at FLARE22 competition. Our annotations, code and models will be made publicly available at: https://github.com/alibaba-damo-academy/Med_Query.

Brain network provides important insights for the diagnosis of many brain disorders, and how to effectively model the brain structure has become one of the core issues in the domain of brain imaging analysis. Recently, various computational methods have been proposed to estimate the causal relationship (i.e., effective connectivity) between brain regions. Compared with traditional correlation-based methods, effective connectivity can provide the direction of information flow, which may provide additional information for the diagnosis of brain diseases. However, existing methods either ignore the fact that there is a temporal-lag in the information transmission across brain regions, or simply set the temporal-lag value between all brain regions to a fixed value. To overcome these issues, we design an effective temporal-lag neural network (termed ETLN) to simultaneously infer the causal relationships and the temporal-lag values between brain regions, which can be trained in an end-to-end manner. In addition, we also introduce three mechanisms to better guide the modeling of brain networks. The evaluation results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrate the effectiveness of the proposed method.

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is typically characterized by randomly sampling a set of latent variables from the latent prior, which is then decoded into possible motions. This joint training of sampling and decoding, however, suffers from posterior collapse as the learned latent variables tend to be ignored by a strong decoder, leading to limited diversity. Alternatively, inspired by the diffusion process in nonequilibrium thermodynamics, we propose MotionDiff, a diffusion probabilistic model to treat the kinematics of human joints as heated particles, which will diffuse from original states to a noise distribution. This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence. Specifically, MotionDiff consists of two parts: a spatial-temporal transformer-based diffusion network to generate diverse yet plausible motions, and a graph convolutional network to further refine the outputs. Experimental results on two datasets demonstrate that our model yields the competitive performance in terms of both accuracy and diversity.

我们为不依赖数据分布满足功能不平等的数据分布或强烈的平滑度假设提供了多项式收敛保证。假设有$ l^2 $准确的分数估计，我们可以为任何有限支撑或足够衰减的尾巴的分布获得Wasserstein距离保证，以及具有进一步平滑度假设的电视保证。

学习优化是一个快速增长的领域，旨在使用机器学习（ML）来解决优化问题或改善现有的优化算法。特别是，图形神经网络（GNN）被认为是用于优化问题的合适ML模型，其变量和约束是置换的 - 例如线性程序（LP）。尽管文献报道了令人鼓舞的数值结果，但本文确定了将GNN应用于解决LP的理论基础。给定LPS的任何尺寸限制，我们构造了一个GNN，该GNN将不同的LP映射到不同的输出。我们表明，正确构建的GNN可以可靠地预测广泛类别中每个LP的可行性，界限和最佳解决方案。我们的证明是基于最近发现的Weisfeiler-Lehman同构测试与GNN之间的联系。为了验证我们的结果，我们培训了一个简单的GNN，并提出了将LP映射到其可行性和解决方案中的准确性。

Wasserstein-Fisher-Rao（WFR）距离是一个指标家族，用于评估两种ra措施的差异，这同时考虑了运输和重量的变化。球形WFR距离是WFR距离的投影版本，以实现概率措施，因此配备了WFR的ra尺度空间可以在概率测量的空间中，用球形WFR视为公式锥。与Wasserstein距离相比，在球形WFR下对大地测量学的理解尚不清楚，并且仍然是持续的研究重点。在本文中，我们开发了一个深度学习框架，以计算球形WFR指标下的大地测量学，并且可以采用学习的大地测量学来生成加权样品。我们的方法基于球形WFR的Benamou-Brenier型动态配方。为了克服重量变化带来的边界约束的困难，将基于反向映射的kullback-leibler（KL）发散术语引入成本函数。此外，引入了使用粒子速度的新的正则化项，以替代汉密尔顿 - 雅各比方程的动态公式中的潜力。当用于样品生成时，与先前的流量模型相比，与给定加权样品的应用相比，我们的框架可能对具有给定加权样品的应用有益。

本文介绍了Z-Code ++，这是一种针对抽象文本摘要优化的新的预训练的语言模型。该模型使用三种技术扩展了艺术编码器模型的状态。首先，我们使用两阶段的预训练过程来改善模型在低资源摘要任务上的性能。该模型首先是使用文本语料库进行语言理解的预先培训的，然后在汇总语料库中不断预先培训，以进行基础文本生成。其次，我们用分离的注意力层代替编码器中的自我发项层，其中每个单词都使用两个向量分别代表其内容和位置。第三，我们使用融合编码器，这是一种以层次方式编码长序列的简单而有效的方法。 Z-Code ++在13个文本摘要任务中的9个跨5种语言中创建了新的艺术状态。我们的模型的参数有效，因为它的表现优于XSUM上600倍较大的Palm-540b，并且在Samsum上的易经的200倍GPT3-175B较大。在零射击和少量设置中，我们的模型大大优于竞争模型。

对于许多应用程序，包括自动驾驶，机器人抓握和增强现实，单眼3D对象检测是一项基本但非常重要的任务。现有的领先方法倾向于首先估算输入图像的深度，并基于点云检测3D对象。该例程遭受了深度估计和对象检测之间固有的差距。此外，预测误差积累也会影响性能。在本文中，提出了一种名为MonopCN的新方法。引入单频道的洞察力是，我们建议在训练期间模拟基于点云的探测器的特征学习行为。因此，在推理期间，学习的特征和预测将与基于点云的检测器相似。为了实现这一目标，我们建议一个场景级仿真模块，一个ROI级别的仿真模块和一个响应级仿真模块，这些模块逐渐用于检测器的完整特征学习和预测管道。我们将我们的方法应用于著名的M3D-RPN检测器和CADDN检测器，并在Kitti和Waymo Open数据集上进行了广泛的实验。结果表明，我们的方法始终提高不同边缘的不同单眼探测器的性能，而无需更改网络体系结构。我们的方法最终达到了最先进的性能。

由于复杂的腹部内形状和腹部器官之间的复杂形状和外观变化，从不同模态的CT成像中进行的准确且健壮的腹部多器官分割是一项具有挑战性的任务。在本文中，我们提出了一个具有分层空间特征调制的概率多器官分割网络，以捕获灵活的器官语义变体，并将学习的变体注入不同的特征图尺度，以进行指导分割。更具体地说，我们通过条件变异自动编码器设计一个输入分解模块，以在低维潜在空间和模型富有器官语义变化上学习器官特异性分布，该分布在输入图像上进行条件。 -NET解码器通过空间特征转换从层次上进行分层，该特征转换能够将变化转换为空间特征映射调制并指导细尺度分割的条件仿射转换参数。提出的方法对公开可用的腹部可用数据集进行了培训，并在其他两个开放数据集上进行了评估，即100个挑战/病理测试，从腹部腹部1K完全监督的腹部器官细分基准和90例TCIA+＆BTCV数据集中进行了90例病例。使用这些数据集用于四个腹部器官，肾脏，脾脏和胰腺，肾脏分数提高了7.3％，胰腺的骰子得分提高了7.7％，而胰腺的骰子得分提高了7.3％，而胰腺的较高速度比强度快7倍，较高的7倍基线分割方法（NNUNET和COTR）。