Our situated environment is full of uncertainty and highly dynamic, thus hindering the widespread adoption of machine-led Intelligent Decision-Making (IDM) in real world scenarios. This means IDM should have the capability of continuously learning new skills and efficiently generalizing across wider applications. IDM benefits from any new approaches and theoretical breakthroughs that exhibit Artificial General Intelligence (AGI) breaking the barriers between tasks and applications. Recent research has well-examined neural architecture, Transformer, as a backbone foundation model and its generalization to various tasks, including computer vision, natural language processing, and reinforcement learning. We therefore argue that a foundation decision model (FDM) can be established by formulating various decision-making tasks as a sequence decoding task using the Transformer architecture; this would be a promising solution to advance the applications of IDM in more complex real world tasks. In this paper, we elaborate on how a foundation decision model improves the efficiency and generalization of IDM. We also discuss potential applications of a FDM in multi-agent game AI, production scheduling, and robotics tasks. Finally, through a case study, we demonstrate our realization of the FDM, DigitalBrain (DB1) with 1.2 billion parameters, which achieves human-level performance over 453 tasks, including text generation, images caption, video games playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 would be a baby step towards more autonomous and efficient real world IDM applications.

User and product information associated with a review is useful for sentiment polarity prediction. Typical approaches incorporating such information focus on modeling users and products as implicitly learned representation vectors. Most do not exploit the potential of historical reviews, or those that currently do require unnecessary modifications to model architecture or do not make full use of user/product associations. The contribution of this work is twofold: i) a method to explicitly employ historical reviews belonging to the same user/product to initialize representations, and ii) efficient incorporation of textual associations between users and products via a user-product cross-context module. Experiments on IMDb, Yelp-2013 and Yelp-2014 benchmarks show that our approach substantially outperforms previous state-of-the-art. Since we employ BERT-base as the encoder, we additionally provide experiments in which our approach performs well with Span-BERT and Longformer. Furthermore, experiments where the reviews of each user/product in the training data are downsampled demonstrate the effectiveness of our approach under a low-resource setting.

In this work, we propose an ID-preserving talking head generation framework, which advances previous methods in two aspects. First, as opposed to interpolating from sparse flow, we claim that dense landmarks are crucial to achieving accurate geometry-aware flow fields. Second, inspired by face-swapping methods, we adaptively fuse the source identity during synthesis, so that the network better preserves the key characteristics of the image portrait. Although the proposed model surpasses prior generation fidelity on established benchmarks, to further make the talking head generation qualified for real usage, personalized fine-tuning is usually needed. However, this process is rather computationally demanding that is unaffordable to standard users. To solve this, we propose a fast adaptation model using a meta-learning approach. The learned model can be adapted to a high-quality personalized model as fast as 30 seconds. Last but not the least, a spatial-temporal enhancement module is proposed to improve the fine details while ensuring temporal coherency. Extensive experiments prove the significant superiority of our approach over the state of the arts in both one-shot and personalized settings.

The ability to associate touch with sight is essential for tasks that require physically interacting with objects in the world. We propose a dataset with paired visual and tactile data called Touch and Go, in which human data collectors probe objects in natural environments using tactile sensors, while simultaneously recording egocentric video. In contrast to previous efforts, which have largely been confined to lab settings or simulated environments, our dataset spans a large number of "in the wild" objects and scenes. To demonstrate our dataset's effectiveness, we successfully apply it to a variety of tasks: 1) self-supervised visuo-tactile feature learning, 2) tactile-driven image stylization, i.e., making the visual appearance of an object more consistent with a given tactile signal, and 3) predicting future frames of a tactile signal from visuo-tactile inputs.

尖峰神经网络（SNN）是一种具有生物学知识的模型，具有高计算能力和低功耗的优势。虽然对深SNN的培训仍然是一个空旷的问题，但它限制了深SNN的现实应用。在这里，我们提出了一个名为Spiking SiamFC ++的深SNN架构，用于对象跟踪，并通过端到端直接培训。具体而言，Alexnet网络在时间域中扩展以提取该功能，并采用替代梯度功能来实现对深SNN的直接监督培训。为了检查尖峰SiAMFC ++的性能，考虑了几种跟踪基准测试，包括OTB2013，OTB2015，Dot2015，Dot2016和UAV123。发现与原始的siAMFC ++相比，精度损失很小。与现有的基于SNN的目标跟踪器相比，例如暹罗（Siamsnn），提议的Spiking SiamFC ++的精度（连续）达到了85.24％（64.37％），远高于52.78％（44.32％）的精度（64.37％）。 。据我们所知，Spiking SiamFC ++的性能优于基于SNN的对象跟踪中现有的最新方法，该方法为目标跟踪领域中的SNN应用提供了新的路径。这项工作可能会进一步促进SNN算法和神经形态芯片的发展。

时间动作定位（TAL）旨在预测未修剪视频（即开始和结束时间）中动作实例的动作类别和时间边界。通常在大多数现有作品中都采用了完全监督的解决方案，并被证明是有效的。这些解决方案中的实际瓶颈之一是所需的大量标记培训数据。为了降低昂贵的人类标签成本，本文着重于很少调查但实用的任务，称为半监督TAL，并提出了一种有效的主动学习方法，名为Al-Stal。我们利用四个步骤来积极选择具有很高信息性的视频样本，并培训本地化模型，名为\ emph {火车，查询，注释，附加}。考虑定位模型的不确定性的两个评分函数配备了ALSTAL，从而促进了视频样本等级和选择。一个人将预测标签分布的熵作为不确定性的度量，称为时间提案熵（TPE）。另一个引入了基于相邻行动建议之间的共同信息的新指标，并评估视频样本的信息性，称为时间上下文不一致（TCI）。为了验证拟议方法的有效性，我们在两个基准数据集Thumos'14和ActivityNet 1.3上进行了广泛的实验。实验结果表明，与完全监督的学习相比，AL-Stal的表现优于现有竞争对手，并实现令人满意的表现。

离线强化学习利用静态数据集来学习最佳策略，无需访问环境。由于代理商在线交互的展示和培训期间的样本数量，这种技术对于多代理学习任务是可取的。然而，在多代理强化学习（Marl）中，从未研究过在线微调的离线预训练的范式从未研究过，可以使用离线MARL研究的数据集或基准。在本文中，我们试图回答违规在Marl中的离线培训是否能够学习一般的政策表现，这些问题可以帮助提高多个下游任务的性能。我们首先引入基于Starcraftia环境的不同质量水平的第一个离线Marl数据集，然后提出了用于有效的离线学习的多代理决策变压器（MADT）的新颖体系结构。 MADT利用变换器的时间表示的建模能力，并将其与离线和在线MARL任务集成。 Madt的一个至关重要的好处是，它学会了可以在不同任务场景下不同类型的代理之间转移的可稳定性政策。当在脱机目的Datline数据上进行评估时，Madt展示了比最先进的离线RL基线的性能卓越。当应用于在线任务时，预先训练的MADT显着提高了样品效率，即使在零射击案件中也享有强大的性能。为了我们的最佳知识，这是第一个研究并展示了在Marl中的样本效率和最常性增强方面的离线预训练模型的有效性。

未经监督的人重新识别（重新ID）由于其解决监督重新ID模型的可扩展性问题而吸引了越来越多的关注。大多数现有的无监督方法采用迭代聚类机制，网络基于由无监督群集生成的伪标签进行培训。但是，聚类错误是不可避免的。为了产生高质量的伪标签并减轻聚类错误的影响，我们提出了一种新的群集关系建模框架，用于无监督的人重新ID。具体地，在聚类之前，基于曲线图相关学习（GCL）模块探索未标记图像之间的关系，然后将其用于聚类以产生高质量的伪标签。本，GCL适自适应地挖掘样本之间的关系迷你批次以减少培训时异常聚类的影响。为了更有效地训练网络，我们进一步提出了一种选择性对比学习（SCL）方法，具有选择性存储器银行更新策略。广泛的实验表明，我们的方法比在Market1501，Dukemtmc-Reid和MSMT17数据集上的大多数最先进的无人监督方法显示出更好的结果。我们将发布模型再现的代码。

公司的在线语义3D分段具有实时RGB-D重建的特殊挑战，例如如何直接在逐步融合的3D几何数据上执行3D卷积，以及如何从帧到帧巧妙地融合信息。我们提出了一种新的融合感知的3D点卷积，其直接在重建的几何表面上运行并有效地利用高质量3D特征学习的帧间相关性。这是由专用动态数据结构启用，该数据结构组织了与全局本地树的在线获取的点云。在全球范围内，我们将在线重建的3D点编译为递增的较长坐标间隔树，从而实现快速点插入和邻域查询。在本地，我们使用OctREE维护每个点的邻居信息，该octree使用全局树的快速查询的构建优势。动态更新的树木更新，并帮助3D卷积有效利用RGB-D帧的有效信息融合的时间一致性。

我们提出了一种新颖的方法，以基于在线RGBD重建与语义分割的在线RGBD重建，提出了一种对未知的室内场景的机器人工作的主动理解。在我们的方法中，探索机器人扫描是由场景中语义对象的识别和分割的驱动和定位。我们的算法基于体积深度融合框架（例如，KinectFusion）之上，并在在线重建卷上执行实时Voxel的语义标记。机器人通过在2D位置和方位角旋转的3D空间上参数化的在线估计的离散观看截由场（VSF）。 VSF为每个网格存储相应视图的分数，测量它减少了几何重建和语义标记的不确定性（熵）。基于VSF，我们选择每个时间步骤的下一个最佳视图（NBV）作为目标。然后，我们通过沿路径和轨迹最大化积分观看分数（信息增益）来共同优化遍历两个相邻的NBV之间的横向路径和相机轨迹。通过广泛的评估，我们表明我们的方法在探索性扫描期间实现了高效准确的在线场景解析。