Scenario-based probabilistic forecasts have become a vital tool to equip decision-makers to address the uncertain nature of renewable energies. To that end, this paper presents a recent promising deep learning generative approach called denoising diffusion probabilistic models. It is a class of latent variable models which have recently demonstrated impressive results in the computer vision community. However, to the best of our knowledge, there has yet to be a demonstration that they can generate high-quality samples of load, PV, or wind power time series, crucial elements to face the new challenges in power systems applications. Thus, we propose the first implementation of this model for energy forecasting using the open data of the Global Energy Forecasting Competition 2014. The results demonstrate this approach is competitive with other state-of-the-art deep learning generative models, including generative adversarial networks, variational autoencoders, and normalizing flows.

Recently, Person Re-Identification (Re-ID) has received a lot of attention. Large datasets containing labeled images of various individuals have been released, allowing researchers to develop and test many successful approaches. However, when such Re-ID models are deployed in new cities or environments, the task of searching for people within a network of security cameras is likely to face an important domain shift, thus resulting in decreased performance. Indeed, while most public datasets were collected in a limited geographic area, images from a new city present different features (e.g., people's ethnicity and clothing style, weather, architecture, etc.). In addition, the whole frames of the video streams must be converted into cropped images of people using pedestrian detection models, which behave differently from the human annotators who created the dataset used for training. To better understand the extent of this issue, this paper introduces a complete methodology to evaluate Re-ID approaches and training datasets with respect to their suitability for unsupervised deployment for live operations. This method is used to benchmark four Re-ID approaches on three datasets, providing insight and guidelines that can help to design better Re-ID pipelines in the future.

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.

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.

A link stream is a set of triplets $(t, u, v)$ indicating that $u$ and $v$ interacted at time $t$. Link streams model numerous datasets and their proper study is crucial in many applications. In practice, raw link streams are often aggregated or transformed into time series or graphs where decisions are made. Yet, it remains unclear how the dynamical and structural information of a raw link stream carries into the transformed object. This work shows that it is possible to shed light into this question by studying link streams via algebraically linear graph and signal operators, for which we introduce a novel linear matrix framework for the analysis of link streams. We show that, due to their linearity, most methods in signal processing can be easily adopted by our framework to analyze the time/frequency information of link streams. However, the availability of linear graph methods to analyze relational/structural information is limited. We address this limitation by developing (i) a new basis for graphs that allow us to decompose them into structures at different resolution levels; and (ii) filters for graphs that allow us to change their structural information in a controlled manner. By plugging-in these developments and their time-domain counterpart into our framework, we are able to (i) obtain a new basis for link streams that allow us to represent them in a frequency-structure domain; and (ii) show that many interesting transformations to link streams, like the aggregation of interactions or their embedding into a euclidean space, can be seen as simple filters in our frequency-structure domain.

This work is on vision-based planning strategies for legged robots that separate locomotion planning into foothold selection and pose adaptation. Current pose adaptation strategies optimize the robot's body pose relative to given footholds. If these footholds are not reached, the robot may end up in a state with no reachable safe footholds. Therefore, we present a Vision-Based Terrain-Aware Locomotion (ViTAL) strategy that consists of novel pose adaptation and foothold selection algorithms. ViTAL introduces a different paradigm in pose adaptation that does not optimize the body pose relative to given footholds, but the body pose that maximizes the chances of the legs in reaching safe footholds. ViTAL plans footholds and poses based on skills that characterize the robot's capabilities and its terrain-awareness. We use the 90 kg HyQ and 140 kg HyQReal quadruped robots to validate ViTAL, and show that they are able to climb various obstacles including stairs, gaps, and rough terrains at different speeds and gaits. We compare ViTAL with a baseline strategy that selects the robot pose based on given selected footholds, and show that ViTAL outperforms the baseline.

城市化及其问题需要对城市动态，尤其是现代城市复杂而多样化的生活方式的深入和全面的了解。数字化的数据可以准确捕获复杂的人类活动，但缺乏人口统计数据的解释性。在本文中，我们研究了美国11个都会区的120万人到110万个地方的出行探访模式的隐私增强数据集，以检测美国最大的美国城市中的潜在行动行为和生活方式。尽管出行访问的复杂性很大，但我们发现生活方式可以自动分解为12种潜在的可解释的活动行为，人们如何将购物，饮食，工作或利用空闲时间结合起来。我们没有描述具有单一生活方式的人，而是发现城市居民的行为是这些行为的混合。那些被检测到的潜在活动行为同样存在于城市之间，无法通过主要人口特征来完全解释。最后，我们发现这些潜在行为与在控制人口特征之后，即使在控制人口特征之后，这些潜在行为也与经验丰富的收入隔离，运输或健康行为有关。我们的结果表明，与活动行为相辅相成，以了解城市动态的重要性。

“感应头”是注意力头，它实现了一种简单的算法来完成令牌序列，例如[a] [b] ... [a] - > [b]。在这项工作中，我们提供了一个假设的初步和间接证据，即诱导头可能构成大型大型变压器模型中所有“文本学习”中大多数的机制（即减少在增加代币指数时损失的损失）。我们发现，诱导头在与秘密学习能力突然急剧上的急剧上升的位置完全相同，这是训练损失的颠簸。我们提出了六种互补的证据，认为诱导头可能是任何大小的变压器模型中一般性内部学习的机理来源。对于仅关注的小型模型，我们提供了有力的因果证据。对于具有MLP的较大模型，我们提供相关证据。

人重新识别（RE-ID）旨在在相机网络中寻找感兴趣的人（查询）。在经典的重新设置中，查询查询在包含整个身体的正确裁剪图像的画廊中。最近，引入了实时重新ID设置，以更好地代表Re-ID的实际应用上下文。它包括在简短的视频中搜索查询，其中包含整个场景帧。最初的实时重新ID基线使用行人探测器来构建大型搜索库和经典的重新ID模型，以在画廊中找到查询。但是，产生的画廊太大，包含低质量的图像，从而降低了现场重新ID性能。在这里，我们提出了一种称为贸易的新现场重新ID方法，以产生较低的高质量画廊。贸易首先使用跟踪算法来识别画廊中同一个人的图像序列。随后，使用异常检测模型选择每个轨道的单个良好代表。贸易已在PRID-2011数据集的实时重新ID版本上进行了验证，并显示出比基线的显着改进。

这项工作提出了两种统计方法，用于基于通用和用户依赖模型的击键生物识别数据的合成。两种方法在机器人检测任务上均经过验证，使用击键合成数据来更好地训练系统。我们的实验包括一个来自168,000名受试者的1.36亿击球事件的数据集。我们通过定性和定量实验分析了两种合成方法的性能。根据两个监督分类器（支持向量机和长期的短期内存网络）和一个包括人类和生成的样本在内的学习框架，考虑了不同的机器人探测器。我们的结果证明，所提出的统计方法能够生成现实的人类合成击键样品。此外，分类结果表明，在具有大型标记数据的情况下，可以高精度检测这些合成样品。但是，在几次学习方案中，它代表了一个重要的挑战。