Warning: this paper contains content that may be offensive or upsetting. In the current context where online platforms have been effectively weaponized in a variety of geo-political events and social issues, Internet memes make fair content moderation at scale even more difficult. Existing work on meme classification and tracking has focused on black-box methods that do not explicitly consider the semantics of the memes or the context of their creation. In this paper, we pursue a modular and explainable architecture for Internet meme understanding. We design and implement multimodal classification methods that perform example- and prototype-based reasoning over training cases, while leveraging both textual and visual SOTA models to represent the individual cases. We study the relevance of our modular and explainable models in detecting harmful memes on two existing tasks: Hate Speech Detection and Misogyny Classification. We compare the performance between example- and prototype-based methods, and between text, vision, and multimodal models, across different categories of harmfulness (e.g., stereotype and objectification). We devise a user-friendly interface that facilitates the comparative analysis of examples retrieved by all of our models for any given meme, informing the community about the strengths and limitations of these explainable methods.

Automation in farming processes is a growing field of research in both academia and industries. A considerable amount of work has been put into this field to develop systems robust enough for farming. Terrace farming, in particular, provides a varying set of challenges, including robust stair climbing methods and stable navigation in unstructured terrains. We propose the design of a novel autonomous terrace farming robot, Aarohi, that can effectively climb steep terraces of considerable heights and execute several farming operations. The design optimisation strategy for the overall mechanical structure is elucidated. Further, the embedded and software architecture along with fail-safe strategies are presented for a working prototype. Algorithms for autonomous traversal over the terrace steps using the scissor lift mechanism and performing various farming operations have also been discussed. The adaptability of the design to specific operational requirements and modular farm tools allow Aarohi to be customised for a wide variety of use cases.

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.

Observational studies have recently received significant attention from the machine learning community due to the increasingly available non-experimental observational data and the limitations of the experimental studies, such as considerable cost, impracticality, small and less representative sample sizes, etc. In observational studies, de-confounding is a fundamental problem of individualised treatment effects (ITE) estimation. This paper proposes disentangled representations with adversarial training to selectively balance the confounders in the binary treatment setting for the ITE estimation. The adversarial training of treatment policy selectively encourages treatment-agnostic balanced representations for the confounders and helps to estimate the ITE in the observational studies via counterfactual inference. Empirical results on synthetic and real-world datasets, with varying degrees of confounding, prove that our proposed approach improves the state-of-the-art methods in achieving lower error in the ITE estimation.

通过各种物体学习各种灵巧的操纵行为仍然是一个开放的巨大挑战。虽然政策学习方法为攻击此问题提供了强大的途径，但它们需要大量的每任务工程和算法调整。本文试图通过开发预先保证的灵巧操纵（PGDM）框架来逃避这些约束，从而在没有任何特定于任务的推理或超级参数调整的情况下会产生各种灵活的操纵行为。 PGD​​M的核心是一种众所周知的机器人构建体，即pre grasps（即用于对象相互作用的手工置序）。这种简单的原始性足以诱导有效的探索策略来获取复杂的灵巧操纵行为。为了详尽地验证这些主张，我们介绍了TCDM，这是根据多个对象和灵巧的操纵器定义的50个不同操纵任务的基准。 TCDM的任务是使用来自各种来源（动画师，人类行为等）的示例对象轨迹自动定义的，而无需任何执行任务工程和/或监督。我们的实验验证了PGDM的探索策略，该策略是由令人惊讶的简单成分（单个预抓姿势）引起的，与先前方法的性能相匹配，这些方法需要昂贵的每任意功能/奖励工程，专家监督和高参数调整。有关动画可视化，训练有素的策略和项目代码，请参阅：https：//pregrasps.github.io/

我们解决了在室内环境中对于具有有限感应功能和有效载荷/功率限制的微型航空车的高效3-D勘探问题。我们开发了一个室内探索框架，该框架利用学习来预测看不见的区域的占用，提取语义特征，样本观点，以预测不同探索目标的信息收益以及计划的信息轨迹，以实现安全和智能的探索。在模拟和实际环境中进行的广泛实验表明，就结构化室内环境中的总路径长度而言，所提出的方法的表现优于最先进的勘探框架，并且在勘探过程中的成功率更高。

参考分辨率旨在识别说话者所引用的实体，在现实世界中更为复杂：新的指称者可以由代理商参与和/或仅仅因为属于共享的物理设置而创建和/或显着。我们的重点是在多模式对话中解决对大屏幕显示上的可视化的引用；至关重要的是，参考分辨率直接参与创建新的可视化的过程。我们描述了通过语言和手势以及新实体建立在大屏幕上出现的可视化的用户引用的注释，这是由于执行用户请求创建新可视化而产生的。我们还描述了我们的参考分辨率管道，该管道依赖于信息状态体系结构来维护对话环境。我们报告有关检测和解决参考文献的结果，模型上下文信息的有效性以及创建可视化的请求不足。我们还尝试了常规的CRF和深度学习 /变压器模型（Bilstm-CRF和Bert-CRF），以在用户话语文本中标记参考。我们的结果表明，尽管CRF仍然表现出色，但转移学习显着提高了深度学习方法的性能，这表明传统方法可能会更好地概括为低资源数据。

在电子健康记录（EHRS）中，不规则的时间序列（ITS）自然发生，这是由于患者健康动态而自然发生，这是由于医院不规则的探访，疾病/状况以及每次访问时测量不同生命迹象的必要性。其目前的培训挑战机器学习算法主要建立在相干固定尺寸特征空间的假设上。在本文中，我们提出了一种新型的连续患者状态感知器模型，称为铜，以应对其在EHR中。铜使用感知器模型和神经普通微分方程（ODE）的概念来学习患者状态的连续时间动态，即输入空间的连续性和输出空间的连续性。神经ODES可以帮助铜生成常规的时间序列，以进食感知器模型，该模型具有处理多模式大规模输入的能力。为了评估所提出的模型的性能，我们在模仿III数据集上使用院内死亡率预测任务，并仔细设计实验来研究不规则性。将结果与证明所提出模型的功效的基准进行了比较。

现代神经网络使用构建块，例如与任意2D翻译一样的卷积。但是，这些香草块并不等于投影歧管中的任意3D翻译。即便如此，所有单眼3D检测器都使用香草块来获得3D坐标，这是为此而不是为香草块设计的任务。本文迈出了朝着探索综合的第一步，以在投影歧管中进行任意3D翻译。由于该深度是最难估计的单眼检测，因此本文提出了深度模棱两可的网络（deviant），该网络（deviant）构建了现有的量表等效性的可检测块。结果，偏差与投影歧管中的深度翻译相等，而香草网络却没有。额外的深度竞争力迫使这种偏差学习一致的深度估计，因此，越来越多的人在纯图像类别中的Kitti和Waymo数据集上实现了最新的单眼3D检测结果，并使用额外信息竞争地对方法进行了竞争性执行。此外，在跨数据库评估中，异常比香草网络更好。 https://github.com/abhi1kumar/deviant的代码和模型

在其表示中，已经发现接受过文本数据训练的神经网络模型编码不希望的语言或敏感属性。删除此类属性是不平凡的，因为属性，文本输入和学习的表示之间存在复杂的关系。最近的工作提出了事后和对抗方法，以从模型的表示中删除此类不需要的属性。通过广泛的理论和经验分析，我们表明这些方法可以适得其反：它们无法完全删除属性，在最坏的情况下，最终可能会破坏所有与任务相关的功能。原因是方法对探测分类器的依赖作为属性的代理。即使在最有利的条件下，当属性在表示空间中的特征可以提供100％的学习探测分类器时，我们证明事后或对抗方法将无法正确删除属性。这些理论含义通过经验实验在合成，多NLI和Twitter数据集的模型上证实。对于敏感的属性去除（例如公平性），我们建议您谨慎使用这些方法，并提出伪造度量，以评估最终分类器的质量。