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.

As the demand for user privacy grows, controlled data removal (machine unlearning) is becoming an important feature of machine learning models for data-sensitive Web applications such as social networks and recommender systems. Nevertheless, at this point it is still largely unknown how to perform efficient machine unlearning of graph neural networks (GNNs); this is especially the case when the number of training samples is small, in which case unlearning can seriously compromise the performance of the model. To address this issue, we initiate the study of unlearning the Graph Scattering Transform (GST), a mathematical framework that is efficient, provably stable under feature or graph topology perturbations, and offers graph classification performance comparable to that of GNNs. Our main contribution is the first known nonlinear approximate graph unlearning method based on GSTs. Our second contribution is a theoretical analysis of the computational complexity of the proposed unlearning mechanism, which is hard to replicate for deep neural networks. Our third contribution are extensive simulation results which show that, compared to complete retraining of GNNs after each removal request, the new GST-based approach offers, on average, a $10.38$x speed-up and leads to a $2.6$% increase in test accuracy during unlearning of $90$ out of $100$ training graphs from the IMDB dataset ($10$% training ratio).

图形结构化数据在实践中无处不在，并且经常使用图神经网络（GNN）处理。随着最近的法律确保``被遗忘的权利''的法律，删除图数据的问题已变得非常重要。为了解决该问题，我们介绍了GNNS的\ emph {认证图形}的第一个已知框架。与标准机器学习相反，在处理复杂的图形数据时，出现了新的分析和启发式学位挑战。首先，需要考虑三种不同类型的未学习请求，包括节点功能，边缘和节点学习。其次，为了建立可证明的绩效保证，需要解决与传播过程中功能混合相关的挑战。简单的图卷积（SGC）及其广泛的Pagerank（GPR）扩展的示例说明了基本分析，从而为GNN的认证未学习奠定了理论基础。我们对六个基准数据集的实证研究表明，与不利用图形信息的完整再培训方法和方法相比，相比之下，表现出色的性能复杂性权衡。例如，当在CORA数据集上学习$ 20 \％$的节点时，我们的方法仅遭受$ 0.1 \％$ $的测试准确性损失，而与完整的再培训相比，提供了$ 4 $倍的加速。我们的方案还胜过未利用图形信息的学习方法，其测试准确性提高了$ 12 \％$，以相当的时间复杂性。

产品空间的嵌入方法是用于复杂数据结构的低失真和低维表示的强大技术。在这里，我们解决了Euclidean，球形和双曲线产品的产品空间形式的线性分类新问题。首先，我们描述了使用测地仪和黎曼·歧木的线性分类器的新型制剂，其使用大气和黎曼指标在向量空间中推广直线和内部产品。其次，我们证明了$ D $ -dimential空间形式的线性分类器的任何曲率具有相同的表现力，即，它们可以粉碎恰好$ d + 1 $积分。第三，我们在产品空间形式中正式化线性分类器，描述了第一个已知的Perceptron和支持这些空间的传染媒介机分类器，并为感知者建立严格的融合结果。此外，我们证明了vapnik-chervonenkis尺寸在尺寸的产品空间形式的线性分类器的维度为\ {至少} $ d + 1 $。我们支持我们的理论发现，在多个数据集上模拟，包括合成数据，图像数据和单细胞RNA测序（SCRNA-SEQ）数据。结果表明，与相同维度的欧几里德空间中的欧几里德空间中，SCRNA-SEQ数据的低维产品空间形式的分类为SCRNA-SEQ数据提供了$ \ SIM15 \％$的性能改进。

This paper introduces a learned hierarchical B-frame coding scheme in response to the Grand Challenge on Neural Network-based Video Coding at ISCAS 2023. We address specifically three issues, including (1) B-frame coding, (2) YUV 4:2:0 coding, and (3) content-adaptive variable-rate coding with only one single model. Most learned video codecs operate internally in the RGB domain for P-frame coding. B-frame coding for YUV 4:2:0 content is largely under-explored. In addition, while there have been prior works on variable-rate coding with conditional convolution, most of them fail to consider the content information. We build our scheme on conditional augmented normalized flows (CANF). It features conditional motion and inter-frame codecs for efficient B-frame coding. To cope with YUV 4:2:0 content, two conditional inter-frame codecs are used to process the Y and UV components separately, with the coding of the UV components conditioned additionally on the Y component. Moreover, we introduce adaptive feature modulation in every convolutional layer, taking into account both the content information and the coding levels of B-frames to achieve content-adaptive variable-rate coding. Experimental results show that our model outperforms x265 and the winner of last year's challenge on commonly used datasets in terms of PSNR-YUV.

Recently, e-scooter-involved crashes have increased significantly but little information is available about the behaviors of on-road e-scooter riders. Most existing e-scooter crash research was based on retrospectively descriptive media reports, emergency room patient records, and crash reports. This paper presents a naturalistic driving study with a focus on e-scooter and vehicle encounters. The goal is to quantitatively measure the behaviors of e-scooter riders in different encounters to help facilitate crash scenario modeling, baseline behavior modeling, and the potential future development of in-vehicle mitigation algorithms. The data was collected using an instrumented vehicle and an e-scooter rider wearable system, respectively. A three-step data analysis process is developed. First, semi-automatic data labeling extracts e-scooter rider images and non-rider human images in similar environments to train an e-scooter-rider classifier. Then, a multi-step scene reconstruction pipeline generates vehicle and e-scooter trajectories in all encounters. The final step is to model e-scooter rider behaviors and e-scooter-vehicle encounter scenarios. A total of 500 vehicle to e-scooter interactions are analyzed. The variables pertaining to the same are also discussed in this paper.

As one of the most popular micro-mobility options, e-scooters are spreading in hundreds of big cities and college towns in the US and worldwide. In the meantime, e-scooters are also posing new challenges to traffic safety. In general, e-scooters are suggested to be ridden in bike lanes/sidewalks or share the road with cars at the maximum speed of about 15-20 mph, which is more flexible and much faster than the pedestrains and bicyclists. These features make e-scooters challenging for human drivers, pedestrians, vehicle active safety modules, and self-driving modules to see and interact. To study this new mobility option and address e-scooter riders' and other road users' safety concerns, this paper proposes a wearable data collection system for investigating the micro-level e-Scooter motion behavior in a Naturalistic road environment. An e-Scooter-based data acquisition system has been developed by integrating LiDAR, cameras, and GPS using the robot operating system (ROS). Software frameworks are developed to support hardware interfaces, sensor operation, sensor synchronization, and data saving. The integrated system can collect data continuously for hours, meeting all the requirements including calibration accuracy and capability of collecting the vehicle and e-Scooter encountering data.

In this paper, we propose SceNDD: a scenario-based naturalistic driving dataset that is built upon data collected from an instrumented vehicle in downtown Indianapolis. The data collection was completed in 68 driving sessions with different drivers, where each session lasted about 20--40 minutes. The main goal of creating this dataset is to provide the research community with real driving scenarios that have diverse trajectories and driving behaviors. The dataset contains ego-vehicle's waypoints, velocity, yaw angle, as well as non-ego actor's waypoints, velocity, yaw angle, entry-time, and exit-time. Certain flexibility is provided to users so that actors, sensors, lanes, roads, and obstacles can be added to the existing scenarios. We used a Joint Probabilistic Data Association (JPDA) tracker to detect non-ego vehicles on the road. We present some preliminary results of the proposed dataset and a few applications associated with it. The complete dataset is expected to be released by early 2023.

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.

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.