机器学习和认知科学的最新工作表明，了解因果信息对于智力的发展至关重要。使用``Blicket otter''环境的认知科学的广泛文献表明，孩子们擅长多种因果推理和学习。我们建议将该环境适应机器​​学习代理。当前机器学习算法的关键挑战之一是建模和理解因果关系：关于因果关系集的可转移抽象假设。相比之下，即使是幼儿也会自发学习和使用因果关系。在这项工作中，我们提出了一个新的基准 - 一种灵活的环境，可以评估可变因果溢出物下的现有技术 - 并证明许多现有的最新方法在这种环境中概括了困难。该基准的代码和资源可在https://github.com/cannylab/casual_overhypothess上获得。

提供强大分布概括和快速适应的学习模型是现代机器学习的关键挑战。将因果结构建模到神经网络中，有望实现稳健的零和几乎没有适应性。可区分因果发现的最新进展提出，将数据生成过程分配到一组模块中，即每个变量的条件分布的一个模块，而只有因果父母仅将因果父母用作预测因素。这种知识模块化分解可以通过仅更新参数的子集来适应分布的转移。在这项工作中，我们通过将其与单片模型和结构化模型进行比较，在该模块上，我们系统地研究了这种模块化神经因果模型的概括和适应性性能，在该模型中，预测因子集不受因果父母的约束。我们的分析表明，模块化神经因果模型在低数据制度中的零和少数适应性上都优于其他模型，并提供了强大的概括。我们还发现，与较密集的图相比，对于稀疏图而言，这种效果更为重要。

在某些研究中，无限的外部存档已用于存储通过进化多目标优化算法发现的所有非主导溶液。已经表明，从存储解决方案中选择的溶液子集通常比最终人群更好。但是，无限档案的使用并不总是现实的。当检查的解决方案数量很大时，我们必须预先指定存档尺寸。在这项研究中，我们检查了存档大小对三个方面的影响：（i）选定的最终解决方案集的质量，（ii）存档维护和最终解决方案集的总计算时间，以及（iii）所需的内存大小。毫不奇怪，存档尺寸的增加可提高最终解决方案集质量。有趣的是，中型存档的总计算时间比小型档案和庞大的档案库（例如，无限档案）大得多。为了减少计算时间，我们检查了两个想法：仅在后代进行定期档案更新和存档。与每一代更新档案库相比，第一个想法可以使用较短的计算时间以略有增加的记忆尺寸来获得几乎相同的最终解决方案设置质量。第二个想法大大减少了计算时间，而最终解决方案集质量的成本略有恶化。 Based on our experimental results, some suggestions are given about how to appropriately choose an archiving strategy and an archive size.

本文着重于当前过度参数化的阴影去除模型的局限性。我们提出了一个新颖的轻型深神经网络，该网络在实验室色彩空间中处理阴影图像。提出的称为“实验室网络”的网络是由以下三个观察结果激励的：首先，实验室颜色空间可以很好地分离亮度信息和颜色属性。其次，顺序堆叠的卷积层无法完全使用来自不同接受场的特征。第三，非阴影区域是重要的先验知识，可以减少阴影和非阴影区域之间的剧烈差异。因此，我们通过涉及两个分支结构的结构来设计实验室网络：L和AB分支。因此，与阴影相关的亮度信息可以很好地处理在L分支中，而颜色属性则很好地保留在AB分支中。此外，每个分支由几个基本块，局部空间注意模块（LSA）和卷积过滤器组成。每个基本块由多个平行的扩张扩张率的扩张卷积组成，以接收不同的接收场，这些接收场具有不同的网络宽度，以节省模型参数和计算成本。然后，构建了增强的通道注意模块（ECA），以从不同的接受场聚集特征，以更好地去除阴影。最后，进一步开发了LSA模块，以充分利用非阴影区域中的先前信息来清洁阴影区域。我们在ISTD和SRD数据集上执行广泛的实验。实验结果表明，我们的实验室网络井胜过最先进的方法。同样，我们的模型参数和计算成本降低了几个数量级。我们的代码可在https://github.com/ngrxmu/lab-net上找到。

In this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset. The proposed benchmark provides drastic appearance variations caused by seasonal changes and diverse weather and illumination conditions. While significant progress has been made in advancing visual SLAM on small-scale datasets with similar conditions, there is still a lack of unified benchmarks representative of real-world scenarios for autonomous driving. We introduce a new unified benchmark for jointly evaluating visual odometry, global place recognition, and map-based visual localization performance which is crucial to successfully enable autonomous driving in any condition. The data has been collected for more than one year, resulting in more than 300 km of recordings in nine different environments ranging from a multi-level parking garage to urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up to centimeter-level accuracy obtained from the fusion of direct stereo-inertial odometry with RTK GNSS. We evaluate the performance of several state-of-the-art visual odometry and visual localization baseline approaches on the benchmark and analyze their properties. The experimental results provide new insights into current approaches and show promising potential for future research. Our benchmark and evaluation protocols will be available at https://www.4seasons-dataset.com/.

Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing significant challenges to accurate scene segmentation and precise object boundary delineation. Prior works either address this issue by post-processing or jointly learn object boundaries to implicitly improve feature encoding of the networks. These approaches often require additional modules which are difficult to integrate into the original architecture. To improve the segmentation near object boundaries, we propose a boundary-aware feature propagation mechanism. This mechanism is achieved by exploiting a multi-task learning framework that aims to explicitly guide the boundaries to their original locations. With one shared encoder, our network outputs (i) boundary localization, (ii) prediction of directions pointing to the object's interior, and (iii) semantic segmentation, in three parallel streams. The predicted boundaries and directions are fused to propagate the learned features to refine the segmentation. We conduct extensive experiments on the S3DIS and SensatUrban datasets against various baseline methods, demonstrating that our proposed approach yields consistent improvements by reducing boundary errors. Our code is available at https://github.com/shenglandu/PushBoundary.

Open vocabulary object detection has been greatly advanced by the recent development of vision-language pretrained model, which helps recognize novel objects with only semantic categories. The prior works mainly focus on knowledge transferring to the object proposal classification and employ class-agnostic box and mask prediction. In this work, we propose CondHead, a principled dynamic network design to better generalize the box regression and mask segmentation for open vocabulary setting. The core idea is to conditionally parameterize the network heads on semantic embedding and thus the model is guided with class-specific knowledge to better detect novel categories. Specifically, CondHead is composed of two streams of network heads, the dynamically aggregated head and the dynamically generated head. The former is instantiated with a set of static heads that are conditionally aggregated, these heads are optimized as experts and are expected to learn sophisticated prediction. The latter is instantiated with dynamically generated parameters and encodes general class-specific information. With such a conditional design, the detection model is bridged by the semantic embedding to offer strongly generalizable class-wise box and mask prediction. Our method brings significant improvement to the state-of-the-art open vocabulary object detection methods with very minor overhead, e.g., it surpasses a RegionClip model by 3.0 detection AP on novel categories, with only 1.1% more computation.

Tongue cancer is a common oral cavity malignancy that originates in the mouth and throat. Much effort has been invested in improving its diagnosis, treatment, and management. Surgical removal, chemotherapy, and radiation therapy remain the major treatment for tongue cancer. The survival of patients determines the treatment effect. Previous studies have identified certain survival and risk factors based on descriptive statistics, ignoring the complex, nonlinear relationship among clinical and demographic variables. In this study, we utilize five cutting-edge machine learning models and clinical data to predict the survival of tongue cancer patients after treatment. Five-fold cross-validation, bootstrap analysis, and permutation feature importance are applied to estimate and interpret model performance. The prognostic factors identified by our method are consistent with previous clinical studies. Our method is accurate, interpretable, and thus useable as additional evidence in tongue cancer treatment and management.

In this paper, we propose a large-scale language pre-training for text GENeration using dIffusion modEl, which is named GENIE. GENIE is a pre-training sequence-to-sequence text generation model which combines Transformer and diffusion. The diffusion model accepts the latent information from the encoder, which is used to guide the denoising of the current time step. After multiple such denoise iterations, the diffusion model can restore the Gaussian noise to the diverse output text which is controlled by the input text. Moreover, such architecture design also allows us to adopt large scale pre-training on the GENIE. We propose a novel pre-training method named continuous paragraph denoise based on the characteristics of the diffusion model. Extensive experiments on the XSum, CNN/DailyMail, and Gigaword benchmarks shows that GENIE can achieves comparable performance with various strong baselines, especially after pre-training, the generation quality of GENIE is greatly improved. We have also conduct a lot of experiments on the generation diversity and parameter impact of GENIE. The code for GENIE will be made publicly available.

We address the theoretical and practical problems related to the trajectory generation and tracking control of tail-sitter UAVs. Theoretically, we focus on the differential flatness property with full exploitation of actual UAV aerodynamic models, which lays a foundation for generating dynamically feasible trajectory and achieving high-performance tracking control. We have found that a tail-sitter is differentially flat with accurate aerodynamic models within the entire flight envelope, by specifying coordinate flight condition and choosing the vehicle position as the flat output. This fundamental property allows us to fully exploit the high-fidelity aerodynamic models in the trajectory planning and tracking control to achieve accurate tail-sitter flights. Particularly, an optimization-based trajectory planner for tail-sitters is proposed to design high-quality, smooth trajectories with consideration of kinodynamic constraints, singularity-free constraints and actuator saturation. The planned trajectory of flat output is transformed to state trajectory in real-time with consideration of wind in environments. To track the state trajectory, a global, singularity-free, and minimally-parameterized on-manifold MPC is developed, which fully leverages the accurate aerodynamic model to achieve high-accuracy trajectory tracking within the whole flight envelope. The effectiveness of the proposed framework is demonstrated through extensive real-world experiments in both indoor and outdoor field tests, including agile SE(3) flight through consecutive narrow windows requiring specific attitude and with speed up to 10m/s, typical tail-sitter maneuvers (transition, level flight and loiter) with speed up to 20m/s, and extremely aggressive aerobatic maneuvers (Wingover, Loop, Vertical Eight and Cuban Eight) with acceleration up to 2.5g.