Unbiased learning to rank (ULTR) studies the problem of mitigating various biases from implicit user feedback data such as clicks, and has been receiving considerable attention recently. A popular ULTR approach for real-world applications uses a two-tower architecture, where click modeling is factorized into a relevance tower with regular input features, and a bias tower with bias-relevant inputs such as the position of a document. A successful factorization will allow the relevance tower to be exempt from biases. In this work, we identify a critical issue that existing ULTR methods ignored - the bias tower can be confounded with the relevance tower via the underlying true relevance. In particular, the positions were determined by the logging policy, i.e., the previous production model, which would possess relevance information. We give both theoretical analysis and empirical results to show the negative effects on relevance tower due to such a correlation. We then propose three methods to mitigate the negative confounding effects by better disentangling relevance and bias. Empirical results on both controlled public datasets and a large-scale industry dataset show the effectiveness of the proposed approaches.

在本文中，我们提出了一个可靠的控制器，该控制器在真正的盲人四足机器人上实现了自然且稳定的快速运动。只有本体感受信息，四足机器人的身体长度最大速度可以移动10倍，并且具有通过各种复杂地形的能力。通过无模型的强化学习，在模拟环境中训练控制器。在本文中，拟议的宽松邻里控制体系结构不仅保证了学习率，而且还获得了一个易于转移到真正四倍的机器人的动作网络。我们的研究发现，训练过程中存在数据对称性损失的问题，这导致学习控制器在左右对称的四倍体机器人结构上的性能不平衡，并提出了一个镜像世界神经网络来解决性能问题。由Mirror-World网络组成的学习控制器可以使机器人具有出色的反扰动能力。训练架构中没有使用特定的人类知识，例如脚部轨迹发生器。学识渊博的控制器可以协调机器人的步态频率和运动速度，并且与人工设计的控制器相比，运动模式更自然，更合理。我们的控制器具有出色的抗扰动性能，并且具有良好的概括能力，可以达到从未学到的运动速度，并且从未见过的地形。

神经图像编码现在表示现有的图像压缩方法。但是，在视频域中仍有很多工作。在这项工作中，我们提出了一部结束了学习的视频编解码器，介绍了几个建筑Noveltize以及培训Noveltizes，围绕适应和关注的概念。我们的编解码器被组织为与帧间编解码器配对的帧内编解码器。作为一种建筑新颖，我们建议培训帧间编解码器模型以基于输入视频的分辨率来调整运动估计处理。第二个建筑新奇是一种新的神经块，它将基于分裂的神经网络和Densenets的概念结合了。最后，我们建议在推理时间内过度装备一组解码器侧乘法参数。通过消融研究和对现有技术的比较，我们在编码收益方面表现出我们所提出的技术的好处。我们将编解码器与VVC / H.266和RLVC进行比较，该rlvc分别代表最先进的传统和端到端学习的编解码器，并在2021年在2021年在2021年执行端到端学习方法竞争，e2e_t_ol。我们的编解码器显然优于E2E_T_OL，并在某些设置中对VVC和RLVC有利地进行比较。

Domain adaptation aims to transfer the knowledge acquired by models trained on (data-rich) source domains to (low-resource) target domains, for which a popular method is invariant representation learning. While they have been studied extensively for classification and regression problems, how they apply to ranking problems, where the data and metrics have a list structure, is not well understood. Theoretically, we establish a domain adaptation generalization bound for ranking under listwise metrics such as MRR and NDCG. The bound suggests an adaptation method via learning list-level domain-invariant feature representations, whose benefits are empirically demonstrated by unsupervised domain adaptation experiments on real-world ranking tasks, including passage reranking. A key message is that for domain adaptation, the representations should be analyzed at the same level at which the metric is computed, as we show that learning invariant representations at the list level is most effective for adaptation on ranking problems.

With the wide applications of colored point cloud in many fields, point cloud perceptual quality assessment plays a vital role in the visual communication systems owing to the existence of quality degradations introduced in various stages. However, the existing point cloud quality assessments ignore the mechanism of human visual system (HVS) which has an important impact on the accuracy of the perceptual quality assessment. In this paper, a progressive knowledge transfer based on human visual perception mechanism for perceptual quality assessment of point clouds (PKT-PCQA) is proposed. The PKT-PCQA merges local features from neighboring regions and global features extracted from graph spectrum. Taking into account the HVS properties, the spatial and channel attention mechanism is also considered in PKT-PCQA. Besides, inspired by the hierarchical perception system of human brains, PKT-PCQA adopts a progressive knowledge transfer to convert the coarse-grained quality classification knowledge to the fine-grained quality prediction task. Experiments on three large and independent point cloud assessment datasets show that the proposed no reference PKT-PCQA network achieves better of equivalent performance comparing with the state-of-the-art full reference quality assessment methods, outperforming the existed no reference quality assessment network.

我们研究了离线模仿学习（IL）的问题，在该问题中，代理商旨在学习最佳的专家行为政策，而无需其他在线环境互动。取而代之的是，该代理来自次优行为的补充离线数据集。解决此问题的先前工作要么要求专家数据占据离线数据集的大部分比例，要么需要学习奖励功能并在以后执行离线加强学习（RL）。在本文中，我们旨在解决问题，而无需进行奖励学习和离线RL培训的其他步骤，当时示范包含大量次优数据。基于行为克隆（BC），我们引入了一个额外的歧视者，以区分专家和非专家数据。我们提出了一个合作框架，以增强这两个任务的学习，基于此框架，我们设计了一种新的IL算法，其中歧视者的输出是BC损失的权重。实验结果表明，与基线算法相比，我们提出的算法可获得更高的回报和更快的训练速度。

多字符分类（MCC）是一个基本机器学习问题，其旨在将每个实例分类为预定义的类集中的一个。鉴于实例，分类模型计算每个类的分数，然后所有类别都用于对类进行排序。分类模型的性能通常通过TOP-K精度/误差（例如，k = 1或5）来测量。在本文中，我们不会旨在提出新的神经表征学习模型，因为最近的作品，但要表明通过排名镜头可以轻松提高MCC性能。特别是，通过将MCC视为对实例的等级等级，我们首先争辩说排名指标，例如归一化的折扣累积增益（NDCG），可以比现有的Top-K度量更具信息化。我们进一步证明主导的神经MCC架构可以用特定的设计选择制定为神经排名框架。基于这种概括，我们表明，利用丰富的信息检索文献利用技术将技术效果简单，直观地将MCC性能从盒子中提高。具有不同数据集和骨干型号的文本和图像分类任务的广泛经验结果（例如，用于文本和图像分类的BERT和RESET）显示了我们提出的框架的价值。

尽管最近的多任务学习和自然语言处理的转移学习成功（NLP），但很少有效地研究了在训练中缩放任务数量的效果。迈出了这一目标，介绍了Exmix（极端混合物）：跨越各个领域和任务家庭的大规模收集107个监督的NLP任务。使用EXMIX，我们研究了最大规模的多任务预培训的影响，并分析了普通任务家庭之间的共同培训转移。通过此分析，我们表明手动策划用于多任务预训练的理想任务，并不简单，而且多任务缩放可以自行改进模型。最后，我们提出了Ext5：使用自我监督跨度去噪和监督EXMIX的多任务目标预先训练的模型。通过广泛的实验，我们表明Ext5优于超级格，宝石，彩虹，封闭书QA任务的强大T5基线，以及Exmix之外的几个任务。 Ext5在预训练时也显着提高了样品效率。

Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than CLS token- and feature-based distillation; 2) An intermediate layer of the teacher network as target perform better than that using the last layer when the depth of the student mismatches that of the teacher; 3) Weak regularization is preferred; etc. With these findings, we achieve significant fine-tuning accuracy improvements over the scratch MIM pre-training on ImageNet-1K classification, using all the ViT-Tiny, ViT-Small, and ViT-base models, with +4.2%/+2.4%/+1.4% gains, respectively. Our TinyMIM model of base size achieves 52.2 mIoU in AE20K semantic segmentation, which is +4.1 higher than the MAE baseline. Our TinyMIM model of tiny size achieves 79.6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget. This strong performance suggests an alternative way for developing small vision Transformer models, that is, by exploring better training methods rather than introducing inductive biases into architectures as in most previous works. Code is available at https://github.com/OliverRensu/TinyMIM.

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.