创建可以自然与人类互动的代理是人工智能（AI）研究中的共同目标。但是，评估这些互动是具有挑战性的：收集在线人类代理相互作用缓慢而昂贵，但更快的代理指标通常与交互式评估相关。在本文中，我们评估了这些现有评估指标的优点，并提出了一种新颖的评估方法，称为标准化测试套件（STS）。 STS使用从真实人类交互数据中挖掘出的行为方案。代理商请参阅重播方案上下文，接收指令，然后将控制权控制以脱机完成交互。记录这些代理的延续并将其发送给人类注释者以将其标记为成功或失败，并且根据其成功的连续性比例对代理进行排名。最终的ST是自然主义相互作用的快速，控制，可解释的和代表的。总的来说，STS巩固了我们许多标准评估指标中所需的许多值，从而使我们能够加速研究进展，以生产可以自然与人类互动的代理。可以在https://youtu.be/yr1tnggorgq上找到视频。

来自科幻小说的普通愿景是机器人将有一天居住在我们的物理空间中，感知世界，才能协助我们的物理劳动力，并通过自然语言与我们沟通。在这里，我们研究如何使用虚拟环境的简化设计如何与人类自然交互的人工代理。我们表明，与自我监督学习的模拟世界中的人类交互的模仿学习足以产生我们称之为MIA的多模式互动剂，这成功与非对抗人类互动75％的时间。我们进一步确定了提高性能的架构和算法技术，例如分层动作选择。完全，我们的结果表明，模仿多模态，实时人类行为可以提供具有丰富的行为的富含性的令人生意的和令人惊讶的有效手段，然后可以为特定目的进行微调，从而铺设基础用于培训互动机器人或数字助理的能力。可以在https://youtu.be/zfgrif7my找到MIA的行为的视频

Cashews are grown by over 3 million smallholders in more than 40 countries worldwide as a principal source of income. As the third largest cashew producer in Africa, Benin has nearly 200,000 smallholder cashew growers contributing 15% of the country's national export earnings. However, a lack of information on where and how cashew trees grow across the country hinders decision-making that could support increased cashew production and poverty alleviation. By leveraging 2.4-m Planet Basemaps and 0.5-m aerial imagery, newly developed deep learning algorithms, and large-scale ground truth datasets, we successfully produced the first national map of cashew in Benin and characterized the expansion of cashew plantations between 2015 and 2021. In particular, we developed a SpatioTemporal Classification with Attention (STCA) model to map the distribution of cashew plantations, which can fully capture texture information from discriminative time steps during a growing season. We further developed a Clustering Augmented Self-supervised Temporal Classification (CASTC) model to distinguish high-density versus low-density cashew plantations by automatic feature extraction and optimized clustering. Results show that the STCA model has an overall accuracy of 80% and the CASTC model achieved an overall accuracy of 77.9%. We found that the cashew area in Benin has doubled from 2015 to 2021 with 60% of new plantation development coming from cropland or fallow land, while encroachment of cashew plantations into protected areas has increased by 70%. Only half of cashew plantations were high-density in 2021, suggesting high potential for intensification. Our study illustrates the power of combining high-resolution remote sensing imagery and state-of-the-art deep learning algorithms to better understand tree crops in the heterogeneous smallholder landscape.

While much attention has been paid to identifying explicit hate speech, implicit hateful expressions that are disguised in coded or indirect language are pervasive and remain a major challenge for existing hate speech detection systems. This paper presents the first attempt to apply Entity Linking (EL) techniques to both explicit and implicit hate speech detection, where we show that such real world knowledge about entity mentions in a text does help models better detect hate speech, and the benefit of adding it into the model is more pronounced when explicit entity triggers (e.g., rally, KKK) are present. We also discuss cases where real world knowledge does not add value to hate speech detection, which provides more insights into understanding and modeling the subtleties of hate speech.

We address the problem of unsupervised domain adaptation when the source domain differs from the target domain because of a shift in the distribution of a latent subgroup. When this subgroup confounds all observed data, neither covariate shift nor label shift assumptions apply. We show that the optimal target predictor can be non-parametrically identified with the help of concept and proxy variables available only in the source domain, and unlabeled data from the target. The identification results are constructive, immediately suggesting an algorithm for estimating the optimal predictor in the target. For continuous observations, when this algorithm becomes impractical, we propose a latent variable model specific to the data generation process at hand. We show how the approach degrades as the size of the shift changes, and verify that it outperforms both covariate and label shift adjustment.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

Runtime monitoring provides a more realistic and applicable alternative to verification in the setting of real neural networks used in industry. It is particularly useful for detecting out-of-distribution (OOD) inputs, for which the network was not trained and can yield erroneous results. We extend a runtime-monitoring approach previously proposed for classification networks to perception systems capable of identification and localization of multiple objects. Furthermore, we analyze its adequacy experimentally on different kinds of OOD settings, documenting the overall efficacy of our approach.

Most benchmarks for studying surgical interventions focus on a specific challenge instead of leveraging the intrinsic complementarity among different tasks. In this work, we present a new experimental framework towards holistic surgical scene understanding. First, we introduce the Phase, Step, Instrument, and Atomic Visual Action recognition (PSI-AVA) Dataset. PSI-AVA includes annotations for both long-term (Phase and Step recognition) and short-term reasoning (Instrument detection and novel Atomic Action recognition) in robot-assisted radical prostatectomy videos. Second, we present Transformers for Action, Phase, Instrument, and steps Recognition (TAPIR) as a strong baseline for surgical scene understanding. TAPIR leverages our dataset's multi-level annotations as it benefits from the learned representation on the instrument detection task to improve its classification capacity. Our experimental results in both PSI-AVA and other publicly available databases demonstrate the adequacy of our framework to spur future research on holistic surgical scene understanding.

Despite the impact of psychiatric disorders on clinical health, early-stage diagnosis remains a challenge. Machine learning studies have shown that classifiers tend to be overly narrow in the diagnosis prediction task. The overlap between conditions leads to high heterogeneity among participants that is not adequately captured by classification models. To address this issue, normative approaches have surged as an alternative method. By using a generative model to learn the distribution of healthy brain data patterns, we can identify the presence of pathologies as deviations or outliers from the distribution learned by the model. In particular, deep generative models showed great results as normative models to identify neurological lesions in the brain. However, unlike most neurological lesions, psychiatric disorders present subtle changes widespread in several brain regions, making these alterations challenging to identify. In this work, we evaluate the performance of transformer-based normative models to detect subtle brain changes expressed in adolescents and young adults. We trained our model on 3D MRI scans of neurotypical individuals (N=1,765). Then, we obtained the likelihood of neurotypical controls and psychiatric patients with early-stage schizophrenia from an independent dataset (N=93) from the Human Connectome Project. Using the predicted likelihood of the scans as a proxy for a normative score, we obtained an AUROC of 0.82 when assessing the difference between controls and individuals with early-stage schizophrenia. Our approach surpassed recent normative methods based on brain age and Gaussian Process, showing the promising use of deep generative models to help in individualised analyses.

The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. Both problems are highly challenging, because hair has complex geometry and appearance, as well as exhibits challenging motion. In this paper, we present a two-stage approach that models hair independently from the head to address these challenges in a data-driven manner. The first stage, state compression, learns a low-dimensional latent space of 3D hair states containing motion and appearance, via a novel autoencoder-as-a-tracker strategy. To better disentangle the hair and head in appearance learning, we employ multi-view hair segmentation masks in combination with a differentiable volumetric renderer. The second stage learns a novel hair dynamics model that performs temporal hair transfer based on the discovered latent codes. To enforce higher stability while driving our dynamics model, we employ the 3D point-cloud autoencoder from the compression stage for de-noising of the hair state. Our model outperforms the state of the art in novel view synthesis and is capable of creating novel hair animations without having to rely on hair observations as a driving signal.