The complicated architecture and high training cost of vision transformers urge the exploration of post-training quantization. However, the heavy-tailed distribution of vision transformer activations hinders the effectiveness of previous post-training quantization methods, even with advanced quantizer designs. Instead of tuning the quantizer to better fit the complicated activation distribution, this paper proposes NoisyQuant, a quantizer-agnostic enhancement for the post-training activation quantization performance of vision transformers. We make a surprising theoretical discovery that for a given quantizer, adding a fixed Uniform noisy bias to the values being quantized can significantly reduce the quantization error under provable conditions. Building on the theoretical insight, NoisyQuant achieves the first success on actively altering the heavy-tailed activation distribution with additive noisy bias to fit a given quantizer. Extensive experiments show NoisyQuant largely improves the post-training quantization performance of vision transformer with minimal computation overhead. For instance, on linear uniform 6-bit activation quantization, NoisyQuant improves SOTA top-1 accuracy on ImageNet by up to 1.7%, 1.1% and 0.5% for ViT, DeiT, and Swin Transformer respectively, achieving on-par or even higher performance than previous nonlinear, mixed-precision quantization.

The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society. The current ABSA works, however, are mostly limited to the scenario of a single text piece, leaving the study in dialogue contexts unexplored. In this work, we introduce a novel task of conversational aspect-based sentiment quadruple analysis, namely DiaASQ, aiming to detect the sentiment quadruple of target-aspect-opinion-sentiment in a dialogue. DiaASQ bridges the gap between fine-grained sentiment analysis and conversational opinion mining. We manually construct a large-scale, high-quality Chinese dataset and also obtain the English version dataset via manual translation. We deliberately propose a neural model to benchmark the task. It advances in effectively performing end-to-end quadruple prediction and manages to incorporate rich dialogue-specific and discourse feature representations for better cross-utterance quadruple extraction. We finally point out several potential future works to facilitate the follow-up research of this new task. The DiaASQ data is open at https://github.com/unikcc/DiaASQ

在这项研究中，我们深入研究了半监督对象检测〜（SSOD）所面临的独特挑战。我们观察到当前的探测器通常遭受3个不一致问题。 1）分配不一致，传统的分配策略对标记噪声很敏感。 2）子任务不一致，其中分类和回归预测在同一特征点未对准。 3）时间不一致，伪Bbox在不同的训练步骤中差异很大。这些问题导致学生网络的优化目标不一致，从而恶化了性能并减慢模型收敛性。因此，我们提出了一个系统的解决方案，称为一致的老师，以补救上述挑战。首先，自适应锚分配代替了基于静态的策略，该策略使学生网络能够抵抗嘈杂的psudo bbox。然后，我们通过设计功能比对模块来校准子任务预测。最后，我们采用高斯混合模型（GMM）来动态调整伪盒阈值。一致的老师在各种SSOD评估上提供了新的强大基线。只有10％的带注释的MS-Coco数据，它可以使用Resnet-50骨干实现40.0 MAP，该数据仅使用伪标签，超过了4个地图。当对完全注释的MS-Coco进行其他未标记的数据进行培训时，性能将进一步增加到49.1 MAP。我们的代码将很快开源。

统一的意见角色标签（ORL）旨在给予一篇文章检测一次拍摄中“意见持有人 - 目标”的所有可能的意见结构。不幸的是，现有的基于转换的统一方法受到更长的意见术语，并且无法解决术语重叠问题。通过采用基于跨度的图形模型实现了当前的最佳性能，然而仍然存在高模型复杂性并且在意见和角色之间的互动不足。在这项工作中，我们通过重新检测转换架构并使用指针网络（PINETNET）来调查新的解决方案。该框架在线性时间复杂度解析了所有意见结构，同时通过限制与PointNet的任何术语的限制。为了实现明确的观点 - 角色互动，我们进一步提出了一个统一的依赖性意见图（UDOG），共同建立了句法依赖结构和部分意见角色结构。然后，我们设计了居中性的图形聚合器（RCGA）以编码多关键udog，其中产生的高阶表示用于促进香草过渡系统中的预测。我们的模型在MPQA基准测试中实现了新的最先进结果。分析进一步证明了我们对疗效和效率的方法的优越性。

Story generation and understanding -- as with all NLG/NLU tasks -- has seen a surge in neurosymbolic work. Researchers have recognized that, while large language models (LLMs) have tremendous utility, they can be augmented with symbolic means to be even better and to make up for any flaws that the neural networks might have. However, symbolic methods are extremely costly in terms of the amount of time and expertise needed to create them. In this work, we capitalize on state-of-the-art Code-LLMs, such as Codex, to bootstrap the use of symbolic methods for tracking the state of stories and aiding in story understanding. We show that our CoRRPUS system and abstracted prompting procedures can beat current state-of-the-art structured LLM techniques on pre-existing story understanding tasks (bAbI task 2 and Re^3) with minimal hand engineering. We hope that this work can help highlight the importance of symbolic representations and specialized prompting for LLMs as these models require some guidance for performing reasoning tasks properly.

随着编码器架构的开发，研究人员能够使用更广泛的数据来研究文本生成任务。其中，KB到文本旨在将一组知识三元转换为人类可读句子。在原始设置中，任务假定输入三元和文本是从具体知识/信息的角度进行对齐的。在本文中，我们扩展了此设置，并探讨了如何促进训练的模型以生成更有信息的文本，即包含有关三重实体但未通过输入三元组传达的更多信息。为了解决这个问题，我们提出了一种新型的内存增强发电机，该发电机采用存储网络来记住培训期间学到的有用知识，并利用此类信息以及输入三元组在操作或测试阶段生成文本。我们从WebNLG中得出一个数据集，以进行新的环境，并进行广泛的实验，以研究我们的模型的有效性以及发现设置的内在特征。

3D重建基于少数学习的新型类别在现实世界中具有吸引力，并吸引了不断增长的研究兴趣。先前的方法主要集中于如何为不同类别设计形状的先验模型。他们在看不见的类别上的表现不是很具竞争力。在本文中，我们提出了一个内存的先验对比网络（MPCN），该网络可以在基于几次学习的3D重建框架中存储形状的先验知识。借助形状记忆，提出了一个多头注意模块以捕获候选形状的不同部分，并将这些部分融合在一起，以指导新型类别的3D重建。此外，我们引入了一种3D吸引的对比学习方法，该方法不仅可以补充内存网络的检索准确性，而且还可以更好地组织下游任务的图像功能。与以前的几次3D重建方法相比，MPCN可以处理类间变异性而无需类别注释。基准合成数据集和Pascal3D+现实世界数据集的实验结果表明，我们的模型的表现明显优于当前的最新方法。

最近，对抗性训练已被纳入自我监督的对比预训练中，以增强标签效率，并具有令人兴奋的对抗性鲁棒性。但是，鲁棒性是经过昂贵的对抗训练的代价。在本文中，我们表明了一个令人惊讶的事实，即对比的预训练与稳健性具有有趣而隐含的联系，并且在经过训练的代表中如此自然的鲁棒性使我们能够设计出一种强大的鲁棒算法，以防止对抗性攻击，Rush，将标准组合在一起。对比的预训练和随机平滑。它提高了标准准确性和强大的精度，并且与对抗训练相比，培训成本大大降低了。我们使用广泛的经验研究表明，拟议中的Rush在一阶攻击下的共同基准（CIFAR-10，CIFAR-100和STL-10）的大幅度优于对抗性训练的强大分类器。特别是，在$ \ ell _ {\ infty} $下 - 大小为8/255 PGD攻击CIFAR-10的标准扰动，我们使用RESNET-18作为骨架达到77.8％的型号达到77.8％稳健精度和87.9％的标准精度。与最先进的工作相比，我们的工作的鲁棒精度提高了15％以上，标准准确性略有提高。

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.

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.