我们提出了Tile2tile，这是一种基于瓷砖平台游戏级别之间的样式转移方法。我们的方法涉及培训模型，这些模型将基于瓷砖提供的低分辨率草图表示的水平转化为给定游戏的原始瓷砖表示。这使这些模型（我们称为过滤器）可以将级别的草图转换为特定游戏的样式。此外，通过将一个游戏的水平转换为草图形式，然后将结果草图转换为另一个游戏的瓷砖，我们获得了两种游戏之间的样式传输方法。我们使用Markov随机字段和自动编码器来学习游戏过滤器，并将其应用于Super Mario Bros，Kid Icarus，Mega Man和Metroid之间的样式转移。

我们提出了一种生成可玩游戏的方法，该游戏使用深层生成潜在变量模型将给定的游戏组合在一起。我们将这种方法称为潜在的组合游戏设计 - 潜在，因为我们使用学习的潜在表示来执行混合，因此组合是因为游戏混合是一种组合创造力过程和游戏设计，因为该方法会生成新颖的可玩游戏。我们使用高斯混合物变化自动编码器（GMVAE），该自动编码器使用高斯人的混合物来对VAE潜在空间进行建模。通过监督的培训，每个组件都学会从一个游戏中编码级别，并让我们将新的混合游戏定义为这些学习组件的线性组合。这使生成新游戏混合了输入游戏，并控制混合中每个游戏的相对比例。我们还使用条件VAE进行了先前的工作，以执行混合并与GMVAE进行比较。我们的结果表明，这两种模型均可生成可玩的混合游戏，以所需的比例将输入游戏融合在一起。

程序内容产生的一个越来越普遍的研究领域是级别的创建：可用于形成更大级别的短片。先前的工作已经使用了基本串联来形成这些较大的级别。但是，即使这些段本身是可完整且形式良好的，串联也可能无法产生可完整的水平，并且可能导致游戏内结构破裂（例如，马里奥中的畸形管道）。我们使用三个基于瓷砖的游戏展示了这一点：一个侧滚动平台游戏，垂直平台游戏和自上而下的Roguelike。此外，我们提出了一个马尔可夫链和一个树搜索算法，该算法在两个级别的段之间找到了一个链接，该级别使用过滤器来确保链接段中的完整性和不间断的游戏内结构。我们进一步表明，这些链接适用于多段级别。我们发现这种方法可靠地找到段之间的链接，并且可以自定义以满足设计师的需求。

We introduce an end-to-end computational framework that enables hyperparameter optimization with the DeepHyper library, accelerated training, and interpretable AI inference with a suite of state-of-the-art AI models, including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-Net. We use these AI models and the benchmark QM9, hMOF, and MD17 datasets to showcase the prediction of user-specified materials properties in modern computing environments, and to demonstrate translational applications for the modeling of small molecules, crystals and metal organic frameworks with a unified, stand-alone framework. We deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership class computing environments.

Many business workflows require extracting important fields from form-like documents (e.g. bank statements, bills of lading, purchase orders, etc.). Recent techniques for automating this task work well only when trained with large datasets. In this work we propose a novel data augmentation technique to improve performance when training data is scarce, e.g. 10-250 documents. Our technique, which we call FieldSwap, works by swapping out the key phrases of a source field with the key phrases of a target field to generate new synthetic examples of the target field for use in training. We demonstrate that this approach can yield 1-7 F1 point improvements in extraction performance.

The most widely studied explainable AI (XAI) approaches are unsound. This is the case with well-known model-agnostic explanation approaches, and it is also the case with approaches based on saliency maps. One solution is to consider intrinsic interpretability, which does not exhibit the drawback of unsoundness. Unfortunately, intrinsic interpretability can display unwieldy explanation redundancy. Formal explainability represents the alternative to these non-rigorous approaches, with one example being PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. Recently, it has been observed that the (absolute) rigor of PI-explanations can be traded off for a smaller explanation size, by computing the so-called relevant sets. Given some positive {\delta}, a set S of features is {\delta}-relevant if, when the features in S are fixed, the probability of getting the target class exceeds {\delta}. However, even for very simple classifiers, the complexity of computing relevant sets of features is prohibitive, with the decision problem being NPPP-complete for circuit-based classifiers. In contrast with earlier negative results, this paper investigates practical approaches for computing relevant sets for a number of widely used classifiers that include Decision Trees (DTs), Naive Bayes Classifiers (NBCs), and several families of classifiers obtained from propositional languages. Moreover, the paper shows that, in practice, and for these families of classifiers, relevant sets are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained for the families of classifiers considered.

Image-text multimodal representation learning aligns data across modalities and enables important medical applications, e.g., image classification, visual grounding, and cross-modal retrieval. In this work, we establish a connection between multimodal representation learning and multiple instance learning. Based on this connection, we propose a generic framework for constructing permutation-invariant score functions with many existing multimodal representation learning approaches as special cases. Furthermore, we use the framework to derive a novel contrastive learning approach and demonstrate that our method achieves state-of-the-art results on a number of downstream tasks.

Meshing is a critical, but user-intensive process necessary for stable and accurate simulations in computational fluid dynamics (CFD). Mesh generation is often a bottleneck in CFD pipelines. Adaptive meshing techniques allow the mesh to be updated automatically to produce an accurate solution for the problem at hand. Existing classical techniques for adaptive meshing require either additional functionality out of solvers, many training simulations, or both. Current machine learning techniques often require substantial computational cost for training data generation, and are restricted in scope to the training data flow regime. MeshDQN is developed as a general purpose deep reinforcement learning framework to iteratively coarsen meshes while preserving target property calculation. A graph neural network based deep Q network is used to select mesh vertices for removal and solution interpolation is used to bypass expensive simulations at each step in the improvement process. MeshDQN requires a single simulation prior to mesh coarsening, while making no assumptions about flow regime, mesh type, or solver, only requiring the ability to modify meshes directly in a CFD pipeline. MeshDQN successfully improves meshes for two 2D airfoils.

The proliferation of unmanned aircraft systems (UAS) has caused airspace regulation authorities to examine the interoperability of these aircraft with collision avoidance systems initially designed for large transport category aircraft. Limitations in the currently mandated TCAS led the Federal Aviation Administration to commission the development of a new solution, the Airborne Collision Avoidance System X (ACAS X), designed to enable a collision avoidance capability for multiple aircraft platforms, including UAS. While prior research explored using deep reinforcement learning algorithms (DRL) for collision avoidance, DRL did not perform as well as existing solutions. This work explores the benefits of using a DRL collision avoidance system whose parameters are tuned using a surrogate optimizer. We show the use of a surrogate optimizer leads to DRL approach that can increase safety and operational viability and support future capability development for UAS collision avoidance.

Communication enables agents to cooperate to achieve their goals. Learning when to communicate, i.e., sparse (in time) communication, and whom to message is particularly important when bandwidth is limited. Recent work in learning sparse individualized communication, however, suffers from high variance during training, where decreasing communication comes at the cost of decreased reward, particularly in cooperative tasks. We use the information bottleneck to reframe sparsity as a representation learning problem, which we show naturally enables lossless sparse communication at lower budgets than prior art. In this paper, we propose a method for true lossless sparsity in communication via Information Maximizing Gated Sparse Multi-Agent Communication (IMGS-MAC). Our model uses two individualized regularization objectives, an information maximization autoencoder and sparse communication loss, to create informative and sparse communication. We evaluate the learned communication `language' through direct causal analysis of messages in non-sparse runs to determine the range of lossless sparse budgets, which allow zero-shot sparsity, and the range of sparse budgets that will inquire a reward loss, which is minimized by our learned gating function with few-shot sparsity. To demonstrate the efficacy of our results, we experiment in cooperative multi-agent tasks where communication is essential for success. We evaluate our model with both continuous and discrete messages. We focus our analysis on a variety of ablations to show the effect of message representations, including their properties, and lossless performance of our model.