过程学习涉及确定键步并确定其逻辑顺序以执行任务。现有方法通常使用第三人称视频来学习该过程，使操纵对象的外观很小，并且经常被演员遮住，从而导致重大错误。相比之下，我们观察到从第一人称（Egentric）可穿戴摄像机获得的视频提供了对动作的毫无开创且清晰的视野。但是，从以eg中心视频学习的程序学习是具有挑战性的，因为（a）由于佩戴者的头部运动，相机视图发生了极端变化，并且（b）由于视频的不受约束性质而存在无关的框架。因此，当前的最新方法的假设是，该动作大约同时发生并且持续时间相同，因此不持有。取而代之的是，我们建议使用视频键位之间的时间对应关系提供的信号。为此，我们提出了一个新颖的自我监督对应和剪切（CNC），用于程序学习。 CNC识别并利用多个视频的键步之间的时间对应关系来学习该过程。我们的实验表明，CNC的表现分别优于基准Procel和Crosstask数据集上的最先进，分别为5.2％和6.3％。此外，对于使用以Egentric视频为中心的程序学习，我们建议使用Egoprocel数据集，该数据集由130名受试者捕获的62个小时的视频组成，执行16个任务。源代码和数据集可在项目页面https://sid2697.github.io/egoprocel/上获得。

在处理极大数量的不同应用程序和平台和根本原因时，调试崩溃的一个重要步骤，是挑战的重要步骤。大规模错误报告系统，例如，Windows错误报告（WER），通常依赖于手动开发的规则和启发式，以使导致崩溃的归咎框架。随着新的应用程序和功能，常规引入和现有应用程序在新环境中运行，开发新规则并维护现有的应用程序变得非常具有挑战性。我们提出了一个数据驱动的解决方案来解决问题。我们从第一个大规模的大规模实证研究开始于362克崩溃，并将其指责的方法报告给在现场运行的成千上万的应用程序。分析为崩溃发生的地点和方式以及如何责备崩溃的方法提供了宝贵的见解。这些洞察力使我们能够开发DeepAnalyze，这是一种用于识别堆栈迹线中的指示框架的新型多任务序列标记方法。我们评估了我们的模型，从四个流行的Microsoft应用程序中获得超过一百万个现实世界崩溃，并显示使用一组应用程序崩溃的DeepAnalyze，不仅可以准确定位相同应用程序的崩溃，还可以为其他应用程序启动崩溃定位零到很少的额外训练数据。

拉力请求是当今协作软件开发和代码审核过程的关键部分。但是，当审阅者或作者不积极参与拉动请求时，拉动请求也可以减慢软件开发过程。在这项工作中，我们设计了一项端到端服务，以提醒作者或审阅者与他们的逾期拉动请求互动，以加速逾期拉动请求。首先，我们根据努力估算和机器学习使用模型来预测给定拉的请求的完成时间。其次，我们使用活动检测来滤除可能逾期的拉请请求，但仍在采取足够的动作。最后，我们使用演员身份证来了解拉动请求的阻止者是谁，并推动适当的演员（作者或审稿人）。轻推的主要新颖性是它成功地减少了拉动请求解决时间，同时确保开发人员认为发送的通知在成千上万的存储库中是有用的。在Microsoft使用的147个存储库的随机试验中，Nudge能够将拉的请求分辨率时间减少60％，而与Nudge未发送通知的逾期拉动请求相比，该请求的8,500次拉。此外，收到推动通知的开发人员将这些通知的73％置于正面。我们观察到在Microsoft的8,000个存储库中扩展Nudge的部署时，我们观察到了类似的结果，在整整一年中，Nudge发送了210,000个通知。这表明了Nudge可以扩展到数千个存储库的能力。最后，我们对选择通知的定性分析指示了未来研究的领域，例如在拉动请求和开发人员的可用性中考虑依赖性。

The rise in data has led to the need for dimension reduction techniques, especially in the area of non-scalar variables, including time series, natural language processing, and computer vision. In this paper, we specifically investigate dimension reduction for time series through functional data analysis. Current methods for dimension reduction in functional data are functional principal component analysis and functional autoencoders, which are limited to linear mappings or scalar representations for the time series, which is inefficient. In real data applications, the nature of the data is much more complex. We propose a non-linear function-on-function approach, which consists of a functional encoder and a functional decoder, that uses continuous hidden layers consisting of continuous neurons to learn the structure inherent in functional data, which addresses the aforementioned concerns in the existing approaches. Our approach gives a low dimension latent representation by reducing the number of functional features as well as the timepoints at which the functions are observed. The effectiveness of the proposed model is demonstrated through multiple simulations and real data examples.

Recently, online social media has become a primary source for new information and misinformation or rumours. In the absence of an automatic rumour detection system the propagation of rumours has increased manifold leading to serious societal damages. In this work, we propose a novel method for building automatic rumour detection system by focusing on oversampling to alleviating the fundamental challenges of class imbalance in rumour detection task. Our oversampling method relies on contextualised data augmentation to generate synthetic samples for underrepresented classes in the dataset. The key idea exploits selection of tweets in a thread for augmentation which can be achieved by introducing a non-random selection criteria to focus the augmentation process on relevant tweets. Furthermore, we propose two graph neural networks(GNN) to model non-linear conversations on a thread. To enhance the tweet representations in our method we employed a custom feature selection technique based on state-of-the-art BERTweet model. Experiments of three publicly available datasets confirm that 1) our GNN models outperform the the current state-of-the-art classifiers by more than 20%(F1-score); 2) our oversampling technique increases the model performance by more than 9%;(F1-score) 3) focusing on relevant tweets for data augmentation via non-random selection criteria can further improve the results; and 4) our method has superior capabilities to detect rumours at very early stage.

Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm. In this paper, we investigate the hypothesis that the ability of a large language model to in-context learn-perform a task is not uniformly spread across all of its underlying components. Using a 66 billion parameter language model (OPT-66B) across a diverse set of 14 downstream tasks, we find this is indeed the case: $\sim$70% of attention heads and $\sim$20% of feed forward networks can be removed with minimal decline in task performance. We find substantial overlap in the set of attention heads (un)important for in-context learning across tasks and number of in-context examples. We also address our hypothesis through a task-agnostic lens, finding that a small set of attention heads in OPT-66B score highly on their ability to perform primitive induction operations associated with in-context learning, namely, prefix matching and copying. These induction heads overlap with task-specific important heads, suggesting that induction heads are among the heads capable of more sophisticated behaviors associated with in-context learning. Overall, our study provides several insights that indicate large language models may be under-trained to perform in-context learning and opens up questions on how to pre-train language models to more effectively perform in-context learning.

$ $With recent advances in CNNs, exceptional improvements have been made in semantic segmentation of high resolution images in terms of accuracy and latency. However, challenges still remain in detecting objects in crowded scenes, large scale variations, partial occlusion, and distortions, while still maintaining mobility and latency. We introduce a fast and efficient convolutional neural network, ASBU-Net, for semantic segmentation of high resolution images that addresses these problems and uses no novelty layers for ease of quantization and embedded hardware support. ASBU-Net is based on a new feature extraction module, atrous space bender layer (ASBL), which is efficient in terms of computation and memory. The ASB layers form a building block that is used to make ASBNet. Since this network does not use any special layers it can be easily implemented, quantized and deployed on FPGAs and other hardware with limited memory. We present experiments on resource and accuracy trade-offs and show strong performance compared to other popular models.

Prompting large language models has enabled significant recent progress in multi-step reasoning over text. However, when applied to text generation from semi-structured data (e.g., graphs or tables), these methods typically suffer from low semantic coverage, hallucination, and logical inconsistency. We propose MURMUR, a neuro-symbolic modular approach to text generation from semi-structured data with multi-step reasoning. MURMUR is a best-first search method that generates reasoning paths using: (1) neural and symbolic modules with specific linguistic and logical skills, (2) a grammar whose production rules define valid compositions of modules, and (3) value functions that assess the quality of each reasoning step. We conduct experiments on two diverse data-to-text generation tasks like WebNLG and LogicNLG. These tasks differ in their data representations (graphs and tables) and span multiple linguistic and logical skills. MURMUR obtains significant improvements over recent few-shot baselines like direct prompting and chain-of-thought prompting, while also achieving comparable performance to fine-tuned GPT-2 on out-of-domain data. Moreover, human evaluation shows that MURMUR generates highly faithful and correct reasoning paths that lead to 26% more logically consistent summaries on LogicNLG, compared to direct prompting.

Vision transformers (ViTs) have achieved impressive results on various computer vision tasks in the last several years. In this work, we study the capability of frozen ViTs, pretrained only on visual data, to generalize to audio-visual data without finetuning any of its original parameters. To do so, we propose a latent audio-visual hybrid (LAVISH) adapter that adapts pretrained ViTs to audio-visual tasks by injecting a small number of trainable parameters into every layer of a frozen ViT. To efficiently fuse visual and audio cues, our LAVISH adapter uses a small set of latent tokens, which form an attention bottleneck, thus, eliminating the quadratic cost of standard cross-attention. Compared to the existing modality-specific audio-visual methods, our approach achieves competitive or even better performance on various audio-visual tasks while using fewer tunable parameters and without relying on costly audio pretraining or external audio encoders. Our code is available at https://genjib.github.io/project_page/LAVISH/

The last several years have witnessed remarkable progress in video-and-language (VidL) understanding. However, most modern VidL approaches use complex and specialized model architectures and sophisticated pretraining protocols, making the reproducibility, analysis and comparisons of these frameworks difficult. Hence, instead of proposing yet another new VidL model, this paper conducts a thorough empirical study demystifying the most important factors in the VidL model design. Among the factors that we investigate are (i) the spatiotemporal architecture design, (ii) the multimodal fusion schemes, (iii) the pretraining objectives, (iv) the choice of pretraining data, (v) pretraining and finetuning protocols, and (vi) dataset and model scaling. Our empirical study reveals that the most important design factors include: temporal modeling, video-to-text multimodal fusion, masked modeling objectives, and joint training on images and videos. Using these empirical insights, we then develop a step-by-step recipe, dubbed VindLU, for effective VidL pretraining. Our final model trained using our recipe achieves comparable or better than state-of-the-art results on several VidL tasks without relying on external CLIP pretraining. In particular, on the text-to-video retrieval task, our approach obtains 61.2% on DiDeMo, and 55.0% on ActivityNet, outperforming current SOTA by 7.8% and 6.1% respectively. Furthermore, our model also obtains state-of-the-art video question-answering results on ActivityNet-QA, MSRVTT-QA, MSRVTT-MC and TVQA. Our code and pretrained models are publicly available at: https://github.com/klauscc/VindLU.