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.

DeepMind的游戏理论与多代理团队研究多学科学习的几个方面，从计算近似值到游戏理论中的基本概念，再到在富裕的空间环境中模拟社会困境，并在困难的团队协调任务中培训3-D类人动物。我们小组的一个签名目的是使用DeepMind在DeepMind中提供的资源和专业知识，以深入强化学习来探索复杂环境中的多代理系统，并使用这些基准来提高我们的理解。在这里，我们总结了我们团队的最新工作，并提出了一种分类法，我们认为这重点介绍了多代理研究中许多重要的开放挑战。

高维计算（HDC）是用于数据表示和学习的范式，起源于计算神经科学。HDC将数据表示为高维，低精度向量，可用于学习或召回等各种信息处理任务。高维空间的映射是HDC中的一个基本问题，现有方法在输入数据本身是高维时会遇到可伸缩性问题。在这项工作中，我们探索了一个基于哈希的流媒体编码技术。我们正式表明，这些方法在学习应用程序的性能方面具有可比的保证，同时比现有替代方案更有效。我们在一个流行的高维分类问题上对这些结果进行了实验验证，并表明我们的方法很容易扩展到非常大的数据集。

我们介绍了DeepNash，这是一种能够学习从头开始播放不完美的信息游戏策略的自主代理，直到人类的专家级别。 Stratego是人工智能（AI）尚未掌握的少数标志性棋盘游戏之一。这个受欢迎的游戏具有$ 10^{535} $节点的巨大游戏树，即，$ 10^{175} $倍的$倍于GO。它具有在不完美的信息下需要决策的其他复杂性，类似于德克萨斯州Hold'em扑克，该扑克的游戏树较小（以$ 10^{164} $节点为单位）。 Stratego中的决策是在许多离散的动作上做出的，而动作与结果之间没有明显的联系。情节很长，在球员获胜之前经常有数百次动作，而Stratego中的情况则不能像扑克中那样轻松地分解成管理大小的子问题。由于这些原因，Stratego几十年来一直是AI领域的巨大挑战，现有的AI方法几乎没有达到业余比赛水平。 Deepnash使用游戏理论，无模型的深钢筋学习方法，而无需搜索，该方法学会通过自我播放来掌握Stratego。 DeepNash的关键组成部分的正则化NASH Dynamics（R-NAD）算法通过直接修改基础多项式学习动力学来收敛到近似NASH平衡，而不是围绕它“循环”。 Deepnash在Stratego中击败了现有的最先进的AI方法，并在Gravon Games平台上获得了年度（2022年）和历史前3名，并与人类专家竞争。

WLANs, which have overtaken wired networks to become the primary means of connecting devices to the Internet, are prone to performance issues due to the scarcity of space in the radio spectrum. As a response, IEEE 802.11ax and subsequent amendments aim at increasing the spatial reuse of a radio channel by allowing the dynamic update of two key parameters in wireless transmission: the transmission power (TX_POWER) and the sensitivity threshold (OBSS_PD). In this paper, we present INSPIRE, a distributed solution performing local Bayesian optimizations based on Gaussian processes to improve the spatial reuse in WLANs. INSPIRE makes no explicit assumptions about the topology of WLANs and favors altruistic behaviors of the access points, leading them to find adequate configurations of their TX_POWER and OBSS_PD parameters for the "greater good" of the WLANs. We demonstrate the superiority of INSPIRE over other state-of-the-art strategies using the ns-3 simulator and two examples inspired by real-life deployments of dense WLANs. Our results show that, in only a few seconds, INSPIRE is able to drastically increase the quality of service of operational WLANs by improving their fairness and throughput.

感知，规划，估算和控制的当代方法允许机器人在不确定，非结构化环境中的远程代理中稳健运行。此进度现在创造了机器人不仅在隔离，而且在我们的复杂环境中运行的机器人。意识到这个机会需要一种高效且灵活的媒介，人类可以与协作机器人沟通。自然语言提供了一种这样的媒体，通过对自然语言理解的统计方法的重大进展，现在能够解释各种自由形式命令。然而，大多数当代方法需要机器人环境的详细，现有的空间语义地图，这些环境模拟了话语可能引用的可能引用的空间。因此，当机器人部署在新的，先前未知或部分观察到的环境中时，这些方法发生故障，特别是当环境的心理模型在人类运营商和机器人之间不同时。本文提供了一种新的学习框架的全面描述，允许现场和服务机器人解释并正确执行先验未知，非结构化环境中的自然语言指令。对于我们的方法而不是我们的语言作为“传感器” - 在话语中隐含的“传感器” - 推断的空间，拓扑和语义信息，然后利用这些信息来学习在潜在环境模型上的分布。我们将此分布纳入概率，语言接地模型中，并在机器人的动作空间的象征性表示中推断出分布。我们使用模仿学习来确定对环境和行为分布的原因的信仰空间政策。我们通过各种导航和移动操纵实验评估我们的框架。

深度加强学习（RL）的最新进展导致许多2人零和游戏中的相当大的进展，如去，扑克和星际争霸。这种游戏的纯粹对抗性质允许概念上简单地应用R1方法。然而，现实世界的设置是许多代理商，代理交互是复杂的共同利益和竞争方面的混合物。我们认为外交，一个旨在突出由多种代理交互导致的困境的7人棋盘游戏。它还具有大型组合动作空间和同时移动，这对RL算法具有具有挑战性。我们提出了一个简单但有效的近似最佳响应操作员，旨在处理大型组合动作空间并同时移动。我们还介绍了一系列近似虚构游戏的政策迭代方法。通过这些方法，我们成功地将RL申请到外交：我们认为我们的代理商令人信服地令人信服地表明，游戏理论均衡分析表明新过程产生了一致的改进。

Recent progress in natural language processing has been driven by advances in both model architecture and model pretraining. Transformer architectures have facilitated building higher-capacity models and pretraining has made it possible to effectively utilize this capacity for a wide variety of tasks. Transformers is an open-source library with the goal of opening up these advances to the wider machine learning community. The library consists of carefully engineered stateof-the art Transformer architectures under a unified API. Backing this library is a curated collection of pretrained models made by and available for the community. Transformers is designed to be extensible by researchers, simple for practitioners, and fast and robust in industrial deployments. The library is available at https://github.com/ huggingface/transformers.

Pennylane是用于量子计算机可区分编程的Python 3软件框架。该库为近期量子计算设备提供了统一的体系结构，支持量子和连续变化的范例。 Pennylane的核心特征是能够以与经典技术（例如反向传播）兼容的方式来计算变异量子电路的梯度。因此，Pennylane扩展了在优化和机器学习中常见的自动分化算法，以包括量子和混合计算。插件系统使该框架与任何基于门的量子模拟器或硬件兼容。我们为硬件提供商提供插件，包括Xanadu Cloud，Amazon Braket和IBM Quantum，允许Pennylane优化在公开访问的量子设备上运行。在古典方面，Pennylane与加速的机器学习库（例如Tensorflow，Pytorch，Jax和Autograd）接口。 Pennylane可用于优化变分的量子本素体，量子近似优化，量子机学习模型和许多其他应用。

View-dependent effects such as reflections pose a substantial challenge for image-based and neural rendering algorithms. Above all, curved reflectors are particularly hard, as they lead to highly non-linear reflection flows as the camera moves. We introduce a new point-based representation to compute Neural Point Catacaustics allowing novel-view synthesis of scenes with curved reflectors, from a set of casually-captured input photos. At the core of our method is a neural warp field that models catacaustic trajectories of reflections, so complex specular effects can be rendered using efficient point splatting in conjunction with a neural renderer. One of our key contributions is the explicit representation of reflections with a reflection point cloud which is displaced by the neural warp field, and a primary point cloud which is optimized to represent the rest of the scene. After a short manual annotation step, our approach allows interactive high-quality renderings of novel views with accurate reflection flow. Additionally, the explicit representation of reflection flow supports several forms of scene manipulation in captured scenes, such as reflection editing, cloning of specular objects, reflection tracking across views, and comfortable stereo viewing. We provide the source code and other supplemental material on https://repo-sam.inria.fr/ fungraph/neural_catacaustics/