对于空中机器人来说，以快速而健壮的方式倒置着陆是一项艰巨的壮举，尤其是完全取决于板载感应和计算。尽管如此，这项壮举通常由蝙蝠，苍蝇和蜜蜂等生物传单进行。我们以前的工作已经确定了一系列板载视觉提示与运动学动作之间的直接因果关系，这些关系允许在小型空中机器人中可靠地执行这种具有挑战性的特技操纵。在这项工作中，我们首先利用深入的强化学习和基于物理的模拟来获得从任何任意方法条件开始的一般最佳控制策略，以实现强大的倒置着陆。这项优化的控制策略提供了从系统的观察空间到其电动机命令动作空间的计算效率映射，包括触发和控制旋转操作。这是通过训练系统在大量和方向变化的大量进式飞行速度上进行训练。接下来，我们通过在仿真中改变了机器人的惯性参数，通过域随机化对学习策略进行了模拟策略的传输和实验验证。通过实验试验，我们确定了几个主要因素，这些因素极大地改善了着陆鲁棒性和确定倒置成功的主要机制。我们希望这项研究中开发的学习框架可以推广以解决更具挑战性的任务，例如利用嘈杂的板载感觉数据，降落在各种方向的表面上或降落在动态移动的表面上。

倒置着陆是一种在空中机器人中执行的具有挑战性的壮举，特别是没有外部定位。然而，它经常通过蜜蜂，苍蝇和蝙蝠等生物传递器进行。我们之前对苍蝇着陆行为的观察表明其推定的视觉提示与所执行的空中机动的运动学之间的开环因果关系。例如，旋转机动程度（因此在触摸之前的身体反转）和腿部辅助体挥杆的量取决于苍蝇的初始体状态，同时接近天花板。在这项工作中，通过使用基于物理的模拟进行实验验证，我们系统地研究了如何优化的倒置着陆操纵如何取决于具有不同幅度和方向的初始接近速度。这是通过分析推定的视觉提示（可在最佳的机动轨迹期间衍生出推定的视觉提示来完成的。我们识别了一个三维策略区域，可以在不使用外部定位数据的情况下开发到全局反转着陆策略的映射。此外，我们还调查了一系列着陆齿轮设计对优化着陆性能的影响，并确定了它们的优缺点。以上使用有限的实验测试部分验证了上述结果，并继续通知并指导我们未来的实验，例如通过应用计算的全球政策。

Adversarial imitation learning (AIL) has become a popular alternative to supervised imitation learning that reduces the distribution shift suffered by the latter. However, AIL requires effective exploration during an online reinforcement learning phase. In this work, we show that the standard, naive approach to exploration can manifest as a suboptimal local maximum if a policy learned with AIL sufficiently matches the expert distribution without fully learning the desired task. This can be particularly catastrophic for manipulation tasks, where the difference between an expert and a non-expert state-action pair is often subtle. We present Learning from Guided Play (LfGP), a framework in which we leverage expert demonstrations of multiple exploratory, auxiliary tasks in addition to a main task. The addition of these auxiliary tasks forces the agent to explore states and actions that standard AIL may learn to ignore. Additionally, this particular formulation allows for the reusability of expert data between main tasks. Our experimental results in a challenging multitask robotic manipulation domain indicate that LfGP significantly outperforms both AIL and behaviour cloning, while also being more expert sample efficient than these baselines. To explain this performance gap, we provide further analysis of a toy problem that highlights the coupling between a local maximum and poor exploration, and also visualize the differences between the learned models from AIL and LfGP.

Location-aware networks will introduce new services and applications for modern convenience, surveillance, and public safety. In this paper, we consider the problem of cooperative localization in a wireless network where the position of certain anchor nodes can be controlled. We introduce an active planning method that aims at moving the anchors such that the information gain of future measurements is maximized. In the control layer of the proposed method, control inputs are calculated by minimizing the traces of approximate inverse Bayesian Fisher information matrixes (FIMs). The estimation layer computes estimates of the agent states and provides Gaussian representations of marginal posteriors of agent positions to the control layer for approximate Bayesian FIM computations. Based on a cost function that accumulates Bayesian FIM contributions over a sliding window of discrete future timesteps, a receding horizon (RH) control is performed. Approximations that make it possible to solve the resulting tree-search problem efficiently are also discussed. A numerical case study demonstrates the intelligent behavior of a single controlled anchor in a 3-D scenario and the resulting significantly improved localization accuracy.

Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from video action recognition (i.e. convolutional pooling, LSTM, TSM) to adapt single-visit convolutional models to handle multiple visit inference. We demonstrate that incorporating images from a patient's past hospital visits provides only a small benefit for the prediction of obstructive hydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, but prediction based on the latest ultrasound is sufficient for patient risk stratification.

Graph Neural Networks (GNNs) have shown great potential in the field of graph representation learning. Standard GNNs define a local message-passing mechanism which propagates information over the whole graph domain by stacking multiple layers. This paradigm suffers from two major limitations, over-squashing and poor long-range dependencies, that can be solved using global attention but significantly increases the computational cost to quadratic complexity. In this work, we propose an alternative approach to overcome these structural limitations by leveraging the ViT/MLP-Mixer architectures introduced in computer vision. We introduce a new class of GNNs, called Graph MLP-Mixer, that holds three key properties. First, they capture long-range dependency and mitigate the issue of over-squashing as demonstrated on the Long Range Graph Benchmark (LRGB) and the TreeNeighbourMatch datasets. Second, they offer better speed and memory efficiency with a complexity linear to the number of nodes and edges, surpassing the related Graph Transformer and expressive GNN models. Third, they show high expressivity in terms of graph isomorphism as they can distinguish at least 3-WL non-isomorphic graphs. We test our architecture on 4 simulated datasets and 7 real-world benchmarks, and show highly competitive results on all of them.

Detecting actions in untrimmed videos should not be limited to a small, closed set of classes. We present a simple, yet effective strategy for open-vocabulary temporal action detection utilizing pretrained image-text co-embeddings. Despite being trained on static images rather than videos, we show that image-text co-embeddings enable openvocabulary performance competitive with fully-supervised models. We show that the performance can be further improved by ensembling the image-text features with features encoding local motion, like optical flow based features, or other modalities, like audio. In addition, we propose a more reasonable open-vocabulary evaluation setting for the ActivityNet data set, where the category splits are based on similarity rather than random assignment.

We present NusaCrowd, a collaborative initiative to collect and unite existing resources for Indonesian languages, including opening access to previously non-public resources. Through this initiative, we have has brought together 137 datasets and 117 standardized data loaders. The quality of the datasets has been assessed manually and automatically, and their effectiveness has been demonstrated in multiple experiments. NusaCrowd's data collection enables the creation of the first zero-shot benchmarks for natural language understanding and generation in Indonesian and its local languages. Furthermore, NusaCrowd brings the creation of the first multilingual automatic speech recognition benchmark in Indonesian and its local languages. Our work is intended to help advance natural language processing research in under-represented languages.

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.

We present a neural flow wavefunction, Gauge-Fermion FlowNet, and use it to simulate 2+1D lattice compact quantum electrodynamics with finite density dynamical fermions. The gauge field is represented by a neural network which parameterizes a discretized flow-based transformation of the amplitude while the fermionic sign structure is represented by a neural net backflow. This approach directly represents the $U(1)$ degree of freedom without any truncation, obeys Guass's law by construction, samples autoregressively avoiding any equilibration time, and variationally simulates Gauge-Fermion systems with sign problems accurately. In this model, we investigate confinement and string breaking phenomena in different fermion density and hopping regimes. We study the phase transition from the charge crystal phase to the vacuum phase at zero density, and observe the phase seperation and the net charge penetration blocking effect under magnetic interaction at finite density. In addition, we investigate a magnetic phase transition due to the competition effect between the kinetic energy of fermions and the magnetic energy of the gauge field. With our method, we further note potential differences on the order of the phase transitions between a continuous $U(1)$ system and one with finite truncation. Our state-of-the-art neural network approach opens up new possibilities to study different gauge theories coupled to dynamical matter in higher dimensions.