We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene. Such a model can be used to produce 3D "remixes" of a given scene, by mapping spatial latent codes into a 3D volumetric representation, which can subsequently be rendered from arbitrary views using physically based volume rendering. By construction, the generated scenes remain view-consistent across arbitrary camera configurations, without any flickering or spatio-temporal artifacts. During training, we employ a combination of 2D, obtained through differentiable volume tracing, and 3D Generative Adversarial Network (GAN) losses, across multiple scales, enforcing realism on both its 3D structure and the 2D renderings. We show results on semi-stochastic scenes of varying scale and complexity, obtained from real and synthetic sources. We demonstrate, for the first time, the feasibility of learning plausible view-consistent 3D scene variations from a single exemplar scene and provide qualitative and quantitative comparisons against recent related methods.

Learning policies from fixed offline datasets is a key challenge to scale up reinforcement learning (RL) algorithms towards practical applications. This is often because off-policy RL algorithms suffer from distributional shift, due to mismatch between dataset and the target policy, leading to high variance and over-estimation of value functions. In this work, we propose variance regularization for offline RL algorithms, using stationary distribution corrections. We show that by using Fenchel duality, we can avoid double sampling issues for computing the gradient of the variance regularizer. The proposed algorithm for offline variance regularization (OVAR) can be used to augment any existing offline policy optimization algorithms. We show that the regularizer leads to a lower bound to the offline policy optimization objective, which can help avoid over-estimation errors, and explains the benefits of our approach across a range of continuous control domains when compared to existing state-of-the-art algorithms.

In the process of materials discovery, chemists currently need to perform many laborious, time-consuming, and often dangerous lab experiments. To accelerate this process, we propose a framework for robots to assist chemists by performing lab experiments autonomously. The solution allows a general-purpose robot to perform diverse chemistry experiments and efficiently make use of available lab tools. Our system can load high-level descriptions of chemistry experiments, perceive a dynamic workspace, and autonomously plan the required actions and motions to perform the given chemistry experiments with common tools found in the existing lab environment. Our architecture uses a modified PDDLStream solver for integrated task and constrained motion planning, which generates plans and motions that are guaranteed to be safe by preventing collisions and spillage. We present a modular framework that can scale to many different experiments, actions, and lab tools. In this work, we demonstrate the utility of our framework on three pouring skills and two foundational chemical experiments for materials synthesis: solubility and recrystallization. More experiments and updated evaluations can be found at https://ac-rad.github.io/arc-icra2023.

Abusive language is a concerning problem in online social media. Past research on detecting abusive language covers different platforms, languages, demographies, etc. However, models trained using these datasets do not perform well in cross-domain evaluation settings. To overcome this, a common strategy is to use a few samples from the target domain to train models to get better performance in that domain (cross-domain few-shot training). However, this might cause the models to overfit the artefacts of those samples. A compelling solution could be to guide the models toward rationales, i.e., spans of text that justify the text's label. This method has been found to improve model performance in the in-domain setting across various NLP tasks. In this paper, we propose RAFT (Rationale Adaptor for Few-shoT classification) for abusive language detection. We first build a multitask learning setup to jointly learn rationales, targets, and labels, and find a significant improvement of 6% macro F1 on the rationale detection task over training solely rationale classifiers. We introduce two rationale-integrated BERT-based architectures (the RAFT models) and evaluate our systems over five different abusive language datasets, finding that in the few-shot classification setting, RAFT-based models outperform baseline models by about 7% in macro F1 scores and perform competitively to models finetuned on other source domains. Furthermore, RAFT-based models outperform LIME/SHAP-based approaches in terms of plausibility and are close in performance in terms of faithfulness.

任务计划可能需要定义有关机器人需要采取行动的世界的无数领域知识。为了改善这项工作，可以使用大型语言模型（LLM）在任务计划期间为潜在的下一个操作评分，甚至直接生成动作序列，鉴于没有其他域信息的自然语言指令。但是，这样的方法要么需要列举所有可能的下一步评分，要么生成可能包含在当前机器人中给定机器人上不可能操作的自由形式文本。我们提出了一个程序化的LLM提示结构，该结构能够跨越位置环境，机器人功能和任务的计划生成功能。我们的关键见解是提示LLM具有环境中可用操作和对象的类似程序的规格，以及可以执行的示例程序。我们通过消融实验提出了有关迅速结构和生成约束的具体建议，证明了虚拟屋家庭任务中最先进的成功率，并将我们的方法部署在桌面任务的物理机器人组上。网站progprompt.github.io

随着共同群众在社交媒体中的参与不断上升，政策制定者/记者在社交媒体上进行在线民意调查以了解人们在特定地点的政治倾向是越来越普遍的。这里的警告是，只有有影响力的人才能进行这样的在线民意调查并大规模伸展。此外，在这种情况下，选民的分配是不可控制的，实际上可能是有偏见的。另一方面，如果我们可以通过社交媒体解释公开可用的数据来探究用户的政治倾向，我们将能够对调查人群有可控的见解，保持低调的成本，并在没有公开数据的情况下收集公开可用的数据涉及有关人员。因此，我们引入了一个自我牵键的半监督框架，以进一步进一步实现这一目标。我们模型的优点是它既不需要大量的培训数据，也不需要存储社交网络参数。然而，它在没有带注释的数据的情况下达到了93.7 \％的精度。此外，每个课程只有几个注释的示例可以实现竞争性能。我们发现，即使在资源约束的设置中，该模型也是高效的，并且从其预测中得出的见解与手动调查结果相匹配时，将其应用于不同的现实生活中。

人口统计学分类对于推荐系统的公平评估或测量在线网络和投票系统中的意外偏见至关重要。教育和政治等重要领域经常为社会平等的未来奠定基础，需要审查设计政策，这些政策可以更好地促进该国人口不平衡的人口分布限制的资源分配平等。我们收集三个公开可用的数据集，以培训性别和种姓分类领域的最先进的分类器。我们在印度背景下对模型进行训练，那里的同名可以拥有不同的造型惯例（一种州的Jolly Abraham/Kumar Abhishikta可以写为Abraham Jolly/Abishikta Kumar）。最后，我们还执行跨测试（在不同数据集上的培训和测试）以了解上述模型的功效。我们还对预测模型执行错误分析。最后，我们试图评估现有印度系统的偏见作为案例研究，并找到一些在性别和种姓层面的次大陆的复杂人口布局中表现出的有趣模式。

今天，参加在线论坛上的讨论非常普遍，这些讨论已经开始对在线用户的整体意见产生强大的影响。 Naturally, twisting the flow of the argument can have a strong impact on the minds of naive users, which in the long run might have socio-political ramifications, for example, winning an election or spreading targeted misinformation.因此，这些平台可能非常容易受到恶意玩家的影响，他们可能会单独采取行动，也可能是繁殖谬误的争论，并动机促进公众舆论。 AD HOMINEM论点是此类谬论中最有效的形式之一。尽管是一个简单的谬论，但它足够有效，可以在离线世界中进行公开辩论，并且可以用作阻止诽谤反对派声音的先驱。在这项工作中，我们迈出了第一步，以阐明野外Ad Hominem谬论的使用。首先，我们建立了一个具有很高准确性的强大AD HOMINEM探测器（F1超过83％，对先前的工作显示出显着改善），即使对于注释的实例构成很小一部分的数据集也是如此。然后，我们在从在线辩论论坛中收集的265k参数（创建者）中使用了我们的检测器。我们的众包调查验证了我们对创建ebate数据的野外预测（94％与手动注释相匹配）。我们的分析表明，令人惊讶的31.23％的创建ebate内容包含AD HOMINEM谬论，并且一群高度活跃的用户的同类发表了更大的AD AD本人，以抑制相反的观点。然后，我们的时间分析表明，自2016年美国总统大选以来，AD HOMINEM论点的使用量显着增加，不仅是政治等主题，而且对于科学和法律。最后，我们讨论了我们的工作的重要意义，以检测和防御AD HOMINEM谬论。

手动相互作用的研究需要为高维多手指模型产生可行的掌握姿势，这通常依赖于分析抓取的合成，从而产生脆弱且不自然的结果。本文介绍了Grasp'd，这是一种与已知模型和视觉输入的可区分接触模拟的掌握方法。我们使用基于梯度的方法作为基于采样的GRASP合成的替代方法，该方法在没有简化假设的情况下失败，例如预先指定的接触位置和本本特征。这样的假设限制了掌握发现，尤其是排除了高接触功率掌握。相比之下，我们基于模拟的方法允许即使对于具有高度自由度的抓地力形态，也可以稳定，高效，物理逼真，高接触抓紧合成。我们确定并解决了对基于梯度的优化进行掌握模拟的挑战，例如非平滑对象表面几何形状，接触稀疏性和坚固的优化景观。 GRASP-D与人类和机器人手模型的分析掌握合成相比，并且结果抓紧超过4倍，超过4倍，从而导致较高的GRASP稳定性。视频和代码可在https://graspd-eccv22.github.io/上获得。

深层语言模型可以是人类认知的解释模型吗？如果是这样，他们的限制是什么？为了探讨这个问题，我们提出了一种称为“超参数假设”的方法，该方法使用预测性超参数调整，以找到认知行为概况的个体描述符。我们通过预测语义流利任务（SFT）中的人类表现迈出了这种方法，这是认知科学中的一项精心研究的任务，从未使用过使用基于变压器的语言模型（TLMS）进行建模。在我们的任务设置中，我们比较了几种方法来预测接下来的单个执行SFT的单词。我们报告了初步证据表明，尽管人们和TLM的学习和使用语言的实施差异明显，但TLMS可用于确定人类流利性任务行为的个体差异，而不是现有计算模型，并且可以提供对人类记忆检索策略的见解 - - 认知过程通常不认为是TLM可以建模的东西。最后，我们讨论了这项工作对知识表示认知建模的含义。