Image token removal is an efficient augmentation strategy for reducing the cost of computing image features. However, this efficient augmentation strategy has been found to adversely affect the accuracy of CLIP-based training. We hypothesize that removing a large portion of image tokens may improperly discard the semantic content associated with a given text description, thus constituting an incorrect pairing target in CLIP training. To address this issue, we propose an attentive token removal approach for CLIP training, which retains tokens with a high semantic correlation to the text description. The correlation scores are computed in an online fashion using the EMA version of the visual encoder. Our experiments show that the proposed attentive masking approach performs better than the previous method of random token removal for CLIP training. The approach also makes it efficient to apply multiple augmentation views to the image, as well as introducing instance contrastive learning tasks between these views into the CLIP framework. Compared to other CLIP improvements that combine different pre-training targets such as SLIP and MaskCLIP, our method is not only more effective, but also much more efficient. Specifically, using ViT-B and YFCC-15M dataset, our approach achieves $43.9\%$ top-1 accuracy on ImageNet-1K zero-shot classification, as well as $62.7/42.1$ and $38.0/23.2$ I2T/T2I retrieval accuracy on Flickr30K and MS COCO, which are $+1.1\%$, $+5.5/+0.9$, and $+4.4/+1.3$ higher than the SLIP method, while being $2.30\times$ faster. An efficient version of our approach running $1.16\times$ faster than the plain CLIP model achieves significant gains of $+5.3\%$, $+11.3/+8.0$, and $+9.5/+4.9$ on these benchmarks.

The pretraining-finetuning paradigm has demonstrated great success in NLP and 2D image fields because of the high-quality representation ability and transferability of their pretrained models. However, pretraining such a strong model is difficult in the 3D point cloud field since the training data is limited and point cloud collection is expensive. This paper introduces \textbf{E}fficient \textbf{P}oint \textbf{C}loud \textbf{L}earning (EPCL), an effective and efficient point cloud learner for directly training high-quality point cloud models with a frozen CLIP model. Our EPCL connects the 2D and 3D modalities by semantically aligning the 2D features and point cloud features without paired 2D-3D data. Specifically, the input point cloud is divided into a sequence of tokens and directly fed into the frozen CLIP model to learn point cloud representation. Furthermore, we design a task token to narrow the gap between 2D images and 3D point clouds. Comprehensive experiments on 3D detection, semantic segmentation, classification and few-shot learning demonstrate that the 2D CLIP model can be an efficient point cloud backbone and our method achieves state-of-the-art accuracy on both real-world and synthetic downstream tasks. Code will be available.

Temporal exponential random graph models (TERGM) are powerful statistical models that can be used to infer the temporal pattern of edge formation and elimination in complex networks (e.g., social networks). TERGMs can also be used in a generative capacity to predict longitudinal time series data in these evolving graphs. However, parameter estimation within this framework fails to capture many real-world properties of social networks, including: triadic relationships, small world characteristics, and social learning theories which could be used to constrain the probabilistic estimation of dyadic covariates. Here, we propose triadic temporal exponential random graph models (TTERGM) to fill this void, which includes these hierarchical network relationships within the graph model. We represent social network learning theory as an additional probability distribution that optimizes Markov chains in the graph vector space. The new parameters are then approximated via Monte Carlo maximum likelihood estimation. We show that our TTERGM model achieves improved fidelity and more accurate predictions compared to several benchmark methods on GitHub network data.

Online forms are widely used to collect data from human and have a multi-billion market. Many software products provide online services for creating semi-structured forms where questions and descriptions are organized by pre-defined structures. However, the design and creation process of forms is still tedious and requires expert knowledge. To assist form designers, in this work we present FormLM to model online forms (by enhancing pre-trained language model with form structural information) and recommend form creation ideas (including question / options recommendations and block type suggestion). For model training and evaluation, we collect the first public online form dataset with 62K online forms. Experiment results show that FormLM significantly outperforms general-purpose language models on all tasks, with an improvement by 4.71 on Question Recommendation and 10.6 on Block Type Suggestion in terms of ROUGE-1 and Macro-F1, respectively.

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.

早期退出是提高深网推理效率的有效范例。通过构建具有不同资源需求的分类器（出口），此类网络可以在早期出口处输出简单的样本，从而消除了执行更深层的需求。尽管现有作品主要关注多EXIT网络的建筑设计，但此类模型的培训策略在很大程度上没有探索。当前的最新模型在培训期间对所有样品进行了相同的处理。但是，在测试过程中的早期外观行为被忽略了，从而导致训练和测试之间存在差距。在本文中，我们建议通过样品加权来弥合这一差距。从直觉上讲，简单的样品通常在推理期间在网络早期退出，应该为培训早期分类器提供更多贡献。但是，晚期分类器应强调硬样品的培训（主要是从更深层退出）。我们的工作建议采用一个体重预测网络，以加重每个出口处不同训练样本的损失。这个重量预测网络和骨干模型在具有新的优化目标的元学习框架下共同优化。通过将推断期间的适应性行为带入训练阶段，我们表明拟议的加权机制始终提高分类准确性和推理效率之间的权衡。代码可在https://github.com/leaplabthu/l2w-den上找到。

推荐系统（RS）是一个重要的在线应用程序，每天都会影响数十亿个用户。主流RS排名框架由两个部分组成：多任务学习模型（MTL），该模型可预测各种用户反馈，即点击，喜欢，分享和多任务融合模型（MTF），该模型（MTF）结合了多任务就用户满意度而言，输出分为最终排名得分。关于融合模型的研究并不多，尽管它对最终建议作为排名的最后一个关键过程有很大的影响。为了优化长期用户满意度，而不是贪婪地获得即时回报，我们将MTF任务作为Markov决策过程（MDP），并在推荐会话中提出，并建议基于批处理加固学习（RL）基于多任务融合框架（BATCHRL-MTF）包括批处理RL框架和在线探索。前者利用批处理RL从固定的批处理数据离线学习最佳推荐政策，以达到长期用户满意度，而后者则探索了潜在的高价值动作在线，以突破本地最佳难题。通过对用户行为的全面调查，我们通过从用户粘性和用户活动性的两个方面的微妙启发式方法对用户满意度进行了建模。最后，我们对十亿个样本级别的现实数据集进行了广泛的实验，以显示模型的有效性。我们建议保守的离线政策估计器（保守 - 访问器）来测试我们的模型离线。此外，我们在真实推荐环境中进行在线实验，以比较不同模型的性能。作为成功在MTF任务中应用的少数批次RL研究之一，我们的模型也已部署在一个大规模的工业短视频平台上，为数亿用户提供服务。

本文从跨模式度量学习的角度来解决基于零点草图的图像检索（ZS-SBIR）问题。此任务具有两个特性：1）零拍摄设置需要具有良好的课堂紧凑性和识别新颖类别的课堂间差异的度量空间，而2）草图查询和照片库是不同的模态。从两个方面，公制学习视点益处ZS-SBIR。首先，它促进了深度度量学习（DML）中最近的良好实践的改进。通过在DML中结合两种基本学习方法，例如分类培训和成对培训，我们为ZS-SBIR设置了一个强大的基线。没有钟声和口哨，这种基线实现了竞争的检索准确性。其次，它提供了一个正确抑制模态间隙至关重要的洞察力。为此，我们设计了一种名为Domency Ippar Triplet硬挖掘（Mathm）的新颖方法。 Mathm增强了基线，具有三种类型的成对学习，例如跨模型样本对，模态样本对，以及它们的组合。\我们还设计了一种自适应加权方法，可以在动态训练期间平衡这三个组件。实验结果证实，Mathm根据强大的基线带来另一轮显着改进，并建立了新的最先进的性能。例如，在Tu-Berlin数据集上，我们达到了47.88 + 2.94％地图@全部和58.28 + 2.34％prip @ 100。代码将在：https://github.com/huangzongheng/mathm公开使用。

准确和高效的点云注册是一个挑战，因为噪音和大量积分影响了对应搜索。这一挑战仍然是一个剩余的研究问题，因为大多数现有方法都依赖于对应搜索。为了解决这一挑战，我们通过调查深生成的神经网络来点云注册来提出新的数据驱动登记算法。给定两个点云，动机是直接生成对齐的点云，这在许多应用中非常有用，如3D匹配和搜索。我们设计了一个端到端的生成神经网络，用于对齐点云生成以实现这种动机，包含三种新组件。首先，提出了一种点多感知层（MLP）混频器（PointMixer）网络以便在自点云中有效地维护全局和局部结构信息。其次，提出了一种特征交互模块来融合来自交叉点云的信息。第三，提出了一种并行和差分样本共识方法来基于所生成的登记结果计算输入点云的变换矩阵。所提出的生成神经网络通过维持数据分布和结构相似度，在GAN框架中训练。 ModelNet40和7Scene数据集的实验表明，所提出的算法实现了最先进的准确性和效率。值得注意的是，与基于最先进的对应的算法相比，我们的方法减少了注册错误（CD）的$ 2 \次数为$ 12 \倍运行时间。

现有的最先进的点描述符仅依赖于结构信息，从而省略纹理信息。然而，纹理信息对于我们的人类来区分场景部分至关重要。此外，基于学习的点描述符是尚不清楚原始点如何贡献到最终描述符的黑框。在本文中，我们提出了一种新的多模式融合方法，通过考虑结构和纹理信息来生成点云注册描述符。具体地，设计一种新的关注融合模块，用于提取描述符提取的加权纹理信息。此外，我们提出了一个可解释的模块来解释有助于最终描述符的原始点。我们使用描述符元素作为对目标层的丢失丢失，并将梯度视为对最终描述符的这一点的重要性。本文进一步移动了一步，以解释注册任务中的深度学习。 3DMATCH，3DLomatch和Kitti的综合实验表明，多模式融合描述符实现最先进的准确性并提高描述符的独特性。我们还表明我们的可解释模块在解释注册描述符提取时。