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.

Robotic force-based compliance control is a preferred approach to achieve high-precision assembly tasks. When the geometric features of assembly objects are asymmetric or irregular, reinforcement learning (RL) agents are gradually incorporated into the compliance controller to adapt to complex force-pose mapping which is hard to model analytically. Since force-pose mapping is strongly dependent on geometric features, a compliance controller is only optimal for current geometric features. To reduce the learning cost of assembly objects with different geometric features, this paper is devoted to answering how to reconfigure existing controllers for new assembly objects with different geometric features. In this paper, model-based parameters are first reconfigured based on the proposed Equivalent Theory of Compliance Law (ETCL). Then the RL agent is transferred based on the proposed Weighted Dimensional Policy Distillation (WDPD) method. The experiment results demonstrate that the control reconfiguration method costs less time and achieves better control performance, which confirms the validity of proposed methods.

机器人舰队的商业和工业部署在处决期间通常会落在遥远的人类遥控者身上，当时机器人处于危险之中或无法取得任务进展。通过持续学习，随着时间的推移，从偏远人类的干预措施也可以用来改善机器人机队控制政策。一个核心问题是如何有效地将人类关注分配给单个机器人。先前的工作在单机器人的单人类设置中解决了这一点。我们正式化了交互式车队学习（IFL）设置，其中多个机器人可以交互查询并向多个人类主管学习。我们提出了一个完全实施的开源IFL基准套件，以评估IFL算法的GPU加速ISAAC健身环境。我们提出了Fleet-Dagger，这是一个IFL算法的家庭，并将一种新颖的Fleet Dagger算法与模拟中的4个基准进行了比较。我们还使用4个ABB Yumi机器人臂进行了1000个物理块式实验试验。实验表明，人类向机器人的分配显着影响机器人车队的性能，并且我们的算法比基线的算法获得了人类努力回报的8.8倍。有关代码，视频和补充材料，请参见https://tinyurl.com/fleet-dagger。

最近的工作表明，2臂“ Fling”运动对于服装平滑可能是有效的。我们考虑单臂弹性运动。与几乎不需要机器人轨迹参数调整的2臂fling运动不同，单臂fling运动对轨迹参数很敏感。我们考虑一个单一的6多机器人臂，该机器人臂学习跨越轨迹以实现高衣覆盖率。给定服装抓握点，机器人在物理实验中探索了不同的参数化fling轨迹。为了提高学习效率，我们提出了一种粗到精细的学习方法，该方法首先使用多军匪徒（MAB）框架有效地找到候选动作，然后通过连续优化方法来完善。此外，我们提出了基于Fling Fall结果不确定性的新颖培训和执行时间停止标准。与基线相比，我们表明所提出的方法显着加速学习。此外，由于通过自学人员收集的类似服装的先前经验，新服装的MAB学习时间最多减少了87％。我们评估了6种服装类型：毛巾，T恤，长袖衬衫，礼服，汗衫和牛仔裤。结果表明，使用先前的经验，机器人需要30分钟以下的时间才能为达到60-94％覆盖率的新型服装学习一项动作。

架子通常用于将物体存储在房屋，商店和仓库中。我们制定了最佳架子布置（OSA）的问题，该目标是优化货架上对象的排列，以便在每个对象的访问频率和移动成本下，以获取访问时间。我们提出了一个混合企业计划（MIP）OSA-MIP，表明它在某些条件下找到了OSA的最佳解决方案，并在其一般成本设置中为其次优的解决方案提供了界限。我们在分析上表征了存在的必要且充分的架子密度条件，因此可以在不从架子上删除物体的情况下检索任何对象。来自1,575架模拟货架试验的实验数据和配备有推动刀片和吸入抓握工具的物理fetch机器人的54次试验表明，安排对象可以最佳地将预期的检索成本降低60-80％，以降低预期的搜索和预期的搜索在部分观察到的配置中，成本增加了50-70％，同时将搜索成功率提高到最高2倍。

由地球观察（EO）卫星收集的数据通常由云覆盖而受到折磨。检测云的存在 - 越来越多地使用深度学习完成 - 在EO应用中是至关重要的预处理。事实上，先进的EO卫星在卫星和下行链路上执行基于深度的学习云检测，只有清晰的天空数据以节省宝贵的带宽。在本文中，我们突出了深度学习的云检测对逆势攻击的脆弱性。通过优化对抗性模式并将其叠加到无云场景中，我们将神经网络偏向于场景中的云中。由于云检测器的输入光谱包括非可见频段，因此我们在多光谱域中生成了我们的攻击。这使得多目标攻击的潜力，特别是在可见带中的云敏感条带和视觉伪装中的对抗偏置。我们还调查了对抗对抗攻击的缓解策略。我们希望我们的工作进一步建立了对EO社区对抗对抗袭击的潜力的认识。

使用单个参数化动态动作操纵可变形物体对蝇钓，宽毯和播放洗牌板等任务非常有用。此类任务作为输入所需的最终状态并输出一个参数化的开环动态机器人动作，它向最终状态产生轨迹。这对于具有涉及摩擦力的复杂动态的长地平轨迹尤其具有挑战性。本文探讨了平面机器人铸造的任务（PRC）：其中握住电缆一端的机器人手腕的一个平面运动使另一端朝向所需的目标滑过平面。 PRC允许电缆达到机器人工作区以外的点，并在家庭，仓库和工厂中具有电缆管理的应用。为了有效地学习给定电缆的PRC策略，我们提出了Real2Sim2Real，一个自动收集物理轨迹示例的自我监督框架，以使用差分演进调谐动态模拟器的参数，生成许多模拟示例，然后使用加权学习策略模拟和物理数据的组合。我们使用三种模拟器，ISAAC健身房分段，ISAAC健身房 - 混合动力和Pybullet，两个功能近似器，高斯工艺和神经网络（NNS），以及具有不同刚度，扭转和摩擦的三个电缆。结果每条电缆的16个举出的测试目标表明，使用ISAAC健身房分段的NN PRC策略达到中位误差距离（电缆长度的百分比），范围为8％至14％，表现优于真实或仅培训的基线和政策。只有模拟的例子。 https://tinyurl.com/robotcast可以使用代码，数据和视频。

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual similarity term between generated and real images (ii) incorporating several techniques from the adversarial training literature including multi-scale training and adaptive discriminator augmentation. The combination of these results in not only better pixel reconstruction but also representations which appear to capture better higher-level details within images. More consequentially, we show how our method, Perceptual MAE, leads to better performance when used for downstream tasks outperforming previous methods. We achieve 78.1% top-1 accuracy linear probing on ImageNet-1K and up to 88.1% when fine-tuning, with similar results for other downstream tasks, all without use of additional pre-trained models or data.

Knowledge representation and reasoning in law are essential to facilitate the automation of legal analysis and decision-making tasks. In this paper, we propose a new approach based on legal science, specifically legal taxonomy, for representing and reasoning with legal documents. Our approach interprets the regulations in legal documents as binary trees, which facilitates legal reasoning systems to make decisions and resolve logical contradictions. The advantages of this approach are twofold. First, legal reasoning can be performed on the basis of the binary tree representation of the regulations. Second, the binary tree representation of the regulations is more understandable than the existing sentence-based representations. We provide an example of how our approach can be used to interpret the regulations in a legal document.

Realistic synthetic image data rendered from 3D models can be used to augment image sets and train image classification semantic segmentation models. In this work, we explore how high quality physically-based rendering and domain randomization can efficiently create a large synthetic dataset based on production 3D CAD models of a real vehicle. We use this dataset to quantify the effectiveness of synthetic augmentation using U-net and Double-U-net models. We found that, for this domain, synthetic images were an effective technique for augmenting limited sets of real training data. We observed that models trained on purely synthetic images had a very low mean prediction IoU on real validation images. We also observed that adding even very small amounts of real images to a synthetic dataset greatly improved accuracy, and that models trained on datasets augmented with synthetic images were more accurate than those trained on real images alone. Finally, we found that in use cases that benefit from incremental training or model specialization, pretraining a base model on synthetic images provided a sizeable reduction in the training cost of transfer learning, allowing up to 90\% of the model training to be front-loaded.