A core process in human cognition is analogical mapping: the ability to identify a similar relational structure between different situations. We introduce a novel task, Visual Analogies of Situation Recognition, adapting the classical word-analogy task into the visual domain. Given a triplet of images, the task is to select an image candidate B' that completes the analogy (A to A' is like B to what?). Unlike previous work on visual analogy that focused on simple image transformations, we tackle complex analogies requiring understanding of scenes. We leverage situation recognition annotations and the CLIP model to generate a large set of 500k candidate analogies. Crowdsourced annotations for a sample of the data indicate that humans agree with the dataset label ~80% of the time (chance level 25%). Furthermore, we use human annotations to create a gold-standard dataset of 3,820 validated analogies. Our experiments demonstrate that state-of-the-art models do well when distractors are chosen randomly (~86%), but struggle with carefully chosen distractors (~53%, compared to 90% human accuracy). We hope our dataset will encourage the development of new analogy-making models. Website: https://vasr-dataset.github.io/

基础模型（FMS）已证明了前所未有的功能，包括零拍学习，高保真数据合成和范围内的概括。但是，正如我们在本文中所显示的那样，FMS在专家任务上的开箱即用表现较差（例如，从语言查询中检索汽车手册技术插图），数据是看不见的，或者属于长尾的数据用于FM预训练的大型数据集的数据分布的一部分。这强调了在此类专家任务上明确评估和芬太尼FMS的必要性，这可以说是在实际现实世界中最重要的任务。在本文中，我们提出了围绕教授FMS了解技术文档的任务，通过学习将其图形插图与相应的语言描述相匹配的任务围绕着了解技术文档的任务。我们的FETA基准重点是公共汽车手册和销售目录手册中的文本对图像和图像到文本检索。 FETA配备了完全自动注释提取的程序（接受后将发布代码），从而使Feta轻松扩展到将来更多的文档类型和应用域。我们的自动注释导致自动性能指标显示，该指标与在人类策划注释中计算的指标一致（也发布）。我们提供多个基线和对FETA的流行FM的分析，从而导致一些有趣的发现，我们认为这对FM社区非常有价值，为现实世界中FMS应用于当前被标准基准的“忽视”的实践专家任务铺平了道路。在常见对象上。

概括跨越不同视觉域的学习表现的能力，例如在真正的照片，剪贴画，绘画和草图之间是人类视觉系统的基本容量。在本文中，不同于利用一些（或全部）源域监控的大多数跨域工作，我们接近一个相对较新的，非常实用的无监督域泛化（UDG）设置在既不源也不在源域中没有培训监督。我们的方法是基于跨域（BRAD）的桥梁​​的自我监督学习 - 辅助桥域附有一组从每个训练域的Brad将视觉（图像到图像）映射保留的一组语义。 BRAD和MAPPAPAPPED（端到端）与对比的自我监督表示模型一起学习（端到端），其用语义对齐每个域将每个域对齐，因此隐含地驱动所有域（见或看不见）语义上彼此对齐。在这项工作中，我们展示了如何使用边缘正则化的布拉德，我们的方法在多个基准和一系列任务中实现了显着的增益，包括UDG，少量UDA和跨多个域数据集的无监督概括（包括指向未经看明域的概念和课程）。

如今，捕获的许多图像仅被机器或人类“观察到”，例如机器人或自动驾驶汽车的摄像机。高级机器视觉模型（例如对象识别或语义分割）假设图像通过相机ISP转换为某些规范的图像空间。但是，相机ISP已优化，用于为人类观察员而不是机器生成视觉上令人愉悦的图像，因此，可以节省ISP计算时间并直接将视觉模型应用于原始数据。然而，已经表明，直接在原始图像上训练这样的模型会导致性能下降。为了减轻性能下降（无需注释原始数据），我们使用了RAW和RGB图像对的数据集，可以轻松获取无人标记的情况。然后，我们通过使用知识蒸馏来训练直接应用于原始数据的模型，以便将原始图像的模型预测与处理后的RGB图像的现成预训练的模型的预测对齐。我们的实验表明，我们在原始图像上进行对象分类和语义分割的性能要比在标记的原始图像上训练的模型要好得多。它还合理地匹配了处理后的RGB图像上预训练模型的预测，同时保存ISP计算开销。

Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to identify driving preferences and produce human-like behavior. However, policies based on imitation learning alone often fail to sufficiently account for safety and reliability concerns. In this paper, we show how imitation learning combined with reinforcement learning using simple rewards can substantially improve the safety and reliability of driving policies over those learned from imitation alone. In particular, we use a combination of imitation and reinforcement learning to train a policy on over 100k miles of urban driving data, and measure its effectiveness in test scenarios grouped by different levels of collision risk. To our knowledge, this is the first application of a combined imitation and reinforcement learning approach in autonomous driving that utilizes large amounts of real-world human driving data.

In intensively managed forests in Europe, where forests are divided into stands of small size and may show heterogeneity within stands, a high spatial resolution (10 - 20 meters) is arguably needed to capture the differences in canopy height. In this work, we developed a deep learning model based on multi-stream remote sensing measurements to create a high-resolution canopy height map over the "Landes de Gascogne" forest in France, a large maritime pine plantation of 13,000 km$^2$ with flat terrain and intensive management. This area is characterized by even-aged and mono-specific stands, of a typical length of a few hundred meters, harvested every 35 to 50 years. Our deep learning U-Net model uses multi-band images from Sentinel-1 and Sentinel-2 with composite time averages as input to predict tree height derived from GEDI waveforms. The evaluation is performed with external validation data from forest inventory plots and a stereo 3D reconstruction model based on Skysat imagery available at specific locations. We trained seven different U-net models based on a combination of Sentinel-1 and Sentinel-2 bands to evaluate the importance of each instrument in the dominant height retrieval. The model outputs allow us to generate a 10 m resolution canopy height map of the whole "Landes de Gascogne" forest area for 2020 with a mean absolute error of 2.02 m on the Test dataset. The best predictions were obtained using all available satellite layers from Sentinel-1 and Sentinel-2 but using only one satellite source also provided good predictions. For all validation datasets in coniferous forests, our model showed better metrics than previous canopy height models available in the same region.

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.

Massive data corpora like WebText, Wikipedia, Conceptual Captions, WebImageText, and LAION have propelled recent dramatic progress in AI. Large neural models trained on such datasets produce impressive results and top many of today's benchmarks. A notable omission within this family of large-scale datasets is 3D data. Despite considerable interest and potential applications in 3D vision, datasets of high-fidelity 3D models continue to be mid-sized with limited diversity of object categories. Addressing this gap, we present Objaverse 1.0, a large dataset of objects with 800K+ (and growing) 3D models with descriptive captions, tags, and animations. Objaverse improves upon present day 3D repositories in terms of scale, number of categories, and in the visual diversity of instances within a category. We demonstrate the large potential of Objaverse via four diverse applications: training generative 3D models, improving tail category segmentation on the LVIS benchmark, training open-vocabulary object-navigation models for Embodied AI, and creating a new benchmark for robustness analysis of vision models. Objaverse can open new directions for research and enable new applications across the field of AI.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

Structure-guided image completion aims to inpaint a local region of an image according to an input guidance map from users. While such a task enables many practical applications for interactive editing, existing methods often struggle to hallucinate realistic object instances in complex natural scenes. Such a limitation is partially due to the lack of semantic-level constraints inside the hole region as well as the lack of a mechanism to enforce realistic object generation. In this work, we propose a learning paradigm that consists of semantic discriminators and object-level discriminators for improving the generation of complex semantics and objects. Specifically, the semantic discriminators leverage pretrained visual features to improve the realism of the generated visual concepts. Moreover, the object-level discriminators take aligned instances as inputs to enforce the realism of individual objects. Our proposed scheme significantly improves the generation quality and achieves state-of-the-art results on various tasks, including segmentation-guided completion, edge-guided manipulation and panoptically-guided manipulation on Places2 datasets. Furthermore, our trained model is flexible and can support multiple editing use cases, such as object insertion, replacement, removal and standard inpainting. In particular, our trained model combined with a novel automatic image completion pipeline achieves state-of-the-art results on the standard inpainting task.