Embedding tables are usually huge in click-through rate (CTR) prediction models. To train and deploy the CTR models efficiently and economically, it is necessary to compress their embedding tables at the training stage. To this end, we formulate a novel quantization training paradigm to compress the embeddings from the training stage, termed low-precision training (LPT). Also, we provide theoretical analysis on its convergence. The results show that stochastic weight quantization has a faster convergence rate and a smaller convergence error than deterministic weight quantization in LPT. Further, to reduce the accuracy degradation, we propose adaptive low-precision training (ALPT) that learns the step size (i.e., the quantization resolution) through gradient descent. Experiments on two real-world datasets confirm our analysis and show that ALPT can significantly improve the prediction accuracy, especially at extremely low bit widths. For the first time in CTR models, we successfully train 8-bit embeddings without sacrificing prediction accuracy. The code of ALPT is publicly available.

In this paper, we present a simple yet surprisingly effective technique to induce "selective amnesia" on a backdoored model. Our approach, called SEAM, has been inspired by the problem of catastrophic forgetting (CF), a long standing issue in continual learning. Our idea is to retrain a given DNN model on randomly labeled clean data, to induce a CF on the model, leading to a sudden forget on both primary and backdoor tasks; then we recover the primary task by retraining the randomized model on correctly labeled clean data. We analyzed SEAM by modeling the unlearning process as continual learning and further approximating a DNN using Neural Tangent Kernel for measuring CF. Our analysis shows that our random-labeling approach actually maximizes the CF on an unknown backdoor in the absence of triggered inputs, and also preserves some feature extraction in the network to enable a fast revival of the primary task. We further evaluated SEAM on both image processing and Natural Language Processing tasks, under both data contamination and training manipulation attacks, over thousands of models either trained on popular image datasets or provided by the TrojAI competition. Our experiments show that SEAM vastly outperforms the state-of-the-art unlearning techniques, achieving a high Fidelity (measuring the gap between the accuracy of the primary task and that of the backdoor) within a few minutes (about 30 times faster than training a model from scratch using the MNIST dataset), with only a small amount of clean data (0.1% of training data for TrojAI models).

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-to-end, learning-based inverse rendering framework incorporating differentiable Monte Carlo raytracing with importance sampling. The framework takes a single image as input to jointly recover the underlying geometry, spatially-varying lighting, and photorealistic materials. Specifically, we introduce a physically-based differentiable rendering layer with screen-space ray tracing, resulting in more realistic specular reflections that match the input photo. In addition, we create a large-scale, photorealistic indoor scene dataset with significantly richer details like complex furniture and dedicated decorations. Further, we design a novel out-of-view lighting network with uncertainty-aware refinement leveraging hypernetwork-based neural radiance fields to predict lighting outside the view of the input photo. Through extensive evaluations on common benchmark datasets, we demonstrate superior inverse rendering quality of our method compared to state-of-the-art baselines, enabling various applications such as complex object insertion and material editing with high fidelity. Code and data will be made available at \url{https://jingsenzhu.github.io/invrend}.

视觉任务的输出格式和相关内容差异很大，因此很难以相同的结构处理它们。一个主要障碍在于对象级别的视觉任务中的高维输出。在本文中，我们提出了一个以对象为中心的视觉框架OBJ2Seq。 OBJ2Seq将对象作为基本单元，并将大多数对象级的视觉任务视为对象的序列生成问题。因此，这些视觉任务可以分为两个步骤。首先识别给定类别的对象，然后为每个对象生成一个序列。输出序列的定义对于不同的任务有所不同，并且通过将这些序列与地面真相目标匹配来监督模型。 OBJ2SEQ能够灵活地确定输入类别以满足自定义要求，并可以轻松扩展到不同的视觉任务。在对MS Coco进行实验时，OBJ2SEQ在对象检测时可获得45.7％的AP，多标签分类的89.0％AP和人类姿势估计的65.0％AP。这些结果证明了其通常应用于不同视觉任务的潜力。代码已在以下网址提供：https：//github.com/casia-iva-lab/obj2seq。

在3D视觉中，视觉重新定位已被广泛讨论：鉴于预构建的3D视觉图，估计查询图像的6 DOF（自由度）姿势。大规模室内环境中的重新定位可实现有吸引力的应用程序，例如增强现实和机器人导航。但是，当相机移动时，在这种环境中，外观变化很快，这对于重新定位系统来说是具有挑战性的。为了解决这个问题，我们建议一种基于虚拟视图综合方法Rendernet，以丰富有关此特定情况的数据库和完善姿势。我们选择直接渲染虚拟观点的必要全局和本地特征，而不是渲染需要高质量3D模型的真实图像，并分别将它们应用于后续图像检索和功能匹配操作中。所提出的方法在很大程度上可以改善大规模室内环境中的性能，例如，在INLOC数据集中获得7.1 \％和12.2 \％的改善。

随着Covid-19的爆发，近年来已经出现了大量相关研究。我们提出了一个基于肺CT扫描图像的自动COVID-19诊断框架，即PVT-COV19D。为了适应图像输入的不同维度，我们首先使用变压器模型对图像进行了分类，然后根据正常分布对数据集中进行采样，并将采样结果馈送到修改的PVTV2模型中以进行训练。COV19-CT-DB数据集上的大量实验证明了该方法的有效性。

通用事件边界检测（GEBD）任务旨在检测通用的，无分类的事件边界，将整个视频分为块。在本文中，我们应用蒙版的自动编码器来提高GEBD任务上的算法性能。我们的方法主要采用了对GEBD任务进行微调的蒙面自动编码器的合奏，并将其作为其他基本模型的自我监督的学习者。此外，我们还使用半监督的伪标签方法来充分利用训练时丰富的未标记动力学-400数据。此外，我们提出了一种软标签方法，以部分平衡正面和负样本，并减轻此任务中模棱两可的标记问题。最后，实施了一个棘手的分割对准策略，以完善我们的模型预测到更准确的位置的边界。通过我们的方法，我们在动力学-GEBD测试集上的F1得分上获得了85.94％的成绩，与2021 Kinetics-GEBD挑战的获胜者相比，F1得分提高了2.31％。我们的代码可从https://github.com/contentandmaterialportortait/mae-gebd获得。

为了根据用户的隐式交互反馈提供点击模拟或相关性估计，在近年来，单击模型进行了很多研究。大多数点击模型都集中在用户行为上，指向单个列表。但是，随着用户界面设计（UI）设计的开发，结果页面上显示的项目的布局往往是多块（即多列表）样式而不是单个列表，这需要不同的假设来建模用户行为模型更精确地。存在桌面上下文中多块页面的单击模型，但是由于不同的互动方式，结果类型，尤其是多块演示样式，因此无法直接应用于移动方案。特别是，多块移动页面通常可以分解为基本垂直块和水平块的交织，从而导致典型的F形式。为了减轻桌面和移动上下文之间的多块页面上的差距，我们进行了用户吸引人的学习研究，并确定用户的顺序浏览，block skip和F-Shape页面上的比较模式。这些发现导致了新型的F形点击模型（FSCM）的设计，该模型是多块移动页面的一般解决方案。首先，我们为每个页面构建一个有向的无环图（DAG），每个项目都被视为顶点，每个边缘表示用户可能的检查流。其次，我们建议分别对用户的顺序（顺序浏览，块跳过）和非序列（比较）行为提出DAG结构的GRU和比较模块。最后，我们将GRU状态和比较模式结合在一起，以执行用户点击预测。与基线模型相比，大型现实世界数据集上的实验验证了FSCM对用户行为预测的有效性。

由于多源信息集成的能力，多视图聚类吸引了很多关注。尽管在过去几十年中已经提出了许多高级方法，但其中大多数通常忽略了弱监督信息的重要性，并且无法保留多种视图的特征属性，从而导致聚类性能不令人满意。为了解决这些问题，在本文中，我们提出了一种新颖的深度观看半监督聚类（DMSC）方法，该方法在网络填充过程中共同优化了三种损失，包括多视图集群损失，半监督的成对约束损失损失和多个自动编码器重建损失。具体而言，基于KL差异的多视图聚类损失被施加在多视图数据的共同表示上，以同时执行异质特征优化，多视图加权和聚类预测。然后，我们通过创新建议将成对约束集成到多视图聚类的过程中，通过执行所学到的必须链接样本的多视图表示（不能链接样本）是相似的（不同的），以便形成的聚类结构可以可以更可信。此外，与现有的竞争对手不同，该竞争对手仅保留网络填充期间每个异质分支的编码器，我们进一步建议调整完整的自动编码器框架，其中包含编码器和解码器。通过这种方式，可以缓解特定视图和视图共享特征空间的严重腐败问题，从而使整个培训程序更加稳定。通过在八个流行图像数据集上进行的全面实验，我们证明了我们提出的方法的性能要比最先进的多视图和单视竞争对手更好。