We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped into three themes: (1) visual navigation, (2) rearrangement, and (3) embodied vision-and-language. We discuss the dominant datasets within each theme, evaluation metrics for the challenges, and the performance of state-of-the-art models. We highlight commonalities between top approaches to the challenges and identify potential future directions for Embodied AI research.

机器学习的普及增加了不公平模型的风险，该模型被部署在高级应用程序中，例如司法系统，药物/疫苗接种设计和医学诊断。尽管有有效的方法可以从头开始训练公平模型，但如何自动揭示和解释受过训练的模型的不公平仍然是一项艰巨的任务。以可解释的方式揭示机器学习模型的不公平是朝着公平和值得信赖的AI迈出的关键一步。在本文中，我们系统地解决了通过挖掘可解释的证据（Rumie）来揭示不公平模型的新任务。关键思想是以一组模型区分的数据实例的形式找到可靠的证据。为了使证据可以解释，我们还找到了一组人为理解的关键属性和决策规则，这些属性和决策规则表征了歧视的数据实例，并将其与其他非歧视数据区分开来。正如在许多现实世界数据集上进行的广泛实验所证明的那样，我们的方法找到了高度可解释和可靠的证据，可以有效揭示受过训练的模型的不公平性。此外，它比所有基线方法更可扩展。

在本文中，我们使用语言数据收集的现场方法讨论了四种低资源印度语语言的演讲语料库的过程中的工作 - Awadhi，Bhojpuri，Braj和Magahi。目前，语料库的总大小约为18小时（每种语言约4-5小时），并用语法信息进行转录和注释，例如词性标签，形态学特征和普遍的依赖关系。我们讨论了以这些语言收集数据的方法，其中大多数是在Covid-19大流行中心进行的，其中之一是为低收入群体带来一些额外的收入，说这些语言。在本文中，我们还讨论了这些语言中自动语音识别系统的基线实验的结果。

我们研究社会上公平$（\ ell_p，k）$的近似算法 - $ m $组的聚类问题，其特殊案例包括社会公平的$ k $ -Median（$ p = 1 $）和社会公平的$ k $ - 均值（$ p = 2 $）问题。我们提出（1）一个多项式时间$（5+2 \ sqrt {6}）^p $ - approximation，最多$ k+m $中心（2）a $（5+2 \ sqrt {6}+\ \ \ \ \ \ \ \ \ \ \ \ \ \\ epsilon）^p $ - approximation with $ k $中心$ n^{2^{o（p）} \ cdot m^2} $，和（3）a $（15+6 \ sqrt {6}） ^p $ k $中心的时间$ k^{m} \ cdot \ text {poly}（n）$。第一个结果是通过使用一系列线性程序的迭代圆形方法的细化来获得的。后两个结果是通过将最多$ K+M $中心的解决方案转换为使用（2）的稀疏方法的$ K $中心的解决方案，并通过详尽的搜索（3）。我们还将算法的性能与现有的双色算法以及基准数据集中的$ K $中心近似算法的恰好比较，并发现我们的算法在实践中也优于现有方法。

语言模型既展示了定量的改进，又展示了新的定性功能，随着规模的增加。尽管它们具有潜在的变革性影响，但这些新能力的特征却很差。为了为未来的研究提供信息，为破坏性的新模型能力做准备，并改善社会有害的效果，至关重要的是，我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战，我们介绍了超越模仿游戏基准（Big Bench）。 Big Bench目前由204个任务组成，由132家机构的442位作者贡献。任务主题是多样的，从语言学，儿童发展，数学，常识性推理，生物学，物理学，社会偏见，软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号，Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为，跨越了数百万到数十亿个参数。此外，一个人类专家评估者团队执行了所有任务，以提供强大的基准。研究结果包括：模型性能和校准都随规模改善，但绝对的术语（以及与评估者的性能相比）；在模型类中的性能非常相似，尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分，而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标；社交偏见通常会随着含糊不清的环境而随着规模而增加，但这可以通过提示来改善。

We introduce Argoverse 2 (AV2) - a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry - sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license.

Object movement identification is one of the most researched problems in the field of computer vision. In this task, we try to classify a pixel as foreground or background. Even though numerous traditional machine learning and deep learning methods already exist for this problem, the two major issues with most of them are the need for large amounts of ground truth data and their inferior performance on unseen videos. Since every pixel of every frame has to be labeled, acquiring large amounts of data for these techniques gets rather expensive. Recently, Zhao et al. [1] proposed one of a kind Arithmetic Distribution Neural Network (ADNN) for universal background subtraction which utilizes probability information from the histogram of temporal pixels and achieves promising results. Building onto this work, we developed an intelligent video surveillance system that uses ADNN architecture for motion detection, trims the video with parts only containing motion, and performs anomaly detection on the trimmed video.

The machine translation mechanism translates texts automatically between different natural languages, and Neural Machine Translation (NMT) has gained attention for its rational context analysis and fluent translation accuracy. However, processing low-resource languages that lack relevant training attributes like supervised data is a current challenge for Natural Language Processing (NLP). We incorporated a technique known Active Learning with the NMT toolkit Joey NMT to reach sufficient accuracy and robust predictions of low-resource language translation. With active learning, a semi-supervised machine learning strategy, the training algorithm determines which unlabeled data would be the most beneficial for obtaining labels using selected query techniques. We implemented two model-driven acquisition functions for selecting the samples to be validated. This work uses transformer-based NMT systems; baseline model (BM), fully trained model (FTM) , active learning least confidence based model (ALLCM), and active learning margin sampling based model (ALMSM) when translating English to Hindi. The Bilingual Evaluation Understudy (BLEU) metric has been used to evaluate system results. The BLEU scores of BM, FTM, ALLCM and ALMSM systems are 16.26, 22.56 , 24.54, and 24.20, respectively. The findings in this paper demonstrate that active learning techniques helps the model to converge early and improve the overall quality of the translation system.

We study the problem of planning under model uncertainty in an online meta-reinforcement learning (RL) setting where an agent is presented with a sequence of related tasks with limited interactions per task. The agent can use its experience in each task and across tasks to estimate both the transition model and the distribution over tasks. We propose an algorithm to meta-learn the underlying structure across tasks, utilize it to plan in each task, and upper-bound the regret of the planning loss. Our bound suggests that the average regret over tasks decreases as the number of tasks increases and as the tasks are more similar. In the classical single-task setting, it is known that the planning horizon should depend on the estimated model's accuracy, that is, on the number of samples within task. We generalize this finding to meta-RL and study this dependence of planning horizons on the number of tasks. Based on our theoretical findings, we derive heuristics for selecting slowly increasing discount factors, and we validate its significance empirically.

As language models have grown in parameters and layers, it has become much harder to train and infer with them on single GPUs. This is severely restricting the availability of large language models such as GPT-3, BERT-Large, and many others. A common technique to solve this problem is pruning the network architecture by removing transformer heads, fully-connected weights, and other modules. The main challenge is to discern the important parameters from the less important ones. Our goal is to find strong metrics for identifying such parameters. We thus propose two strategies: Cam-Cut based on the GradCAM interpretations, and Smooth-Cut based on the SmoothGrad, for calculating the importance scores. Through this work, we show that our scoring functions are able to assign more relevant task-based scores to the network parameters, and thus both our pruning approaches significantly outperform the standard weight and gradient-based strategies, especially at higher compression ratios in BERT-based models. We also analyze our pruning masks and find them to be significantly different from the ones obtained using standard metrics.