Several works have demonstrated the use of variational autoencoders (VAEs) for generating levels in the style of existing games and blending levels across different games. Further, quality-diversity (QD) algorithms have also become popular for generating varied game content by using evolution to explore a search space while focusing on both variety and quality. To reap the benefits of both these approaches, we present a level generation and game blending approach that combines the use of VAEs and QD algorithms. Specifically, we train VAEs on game levels and run the MAP-Elites QD algorithm using the learned latent space of the VAE as the search space. The latent space captures the properties of the games whose levels we want to generate and blend, while MAP-Elites searches this latent space to find a diverse set of levels optimizing a given objective such as playability. We test our method using models for 5 different platformer games as well as a blended domain spanning 3 of these games. We refer to using MAP-Elites for blending as Blend-Elites. Our results show that MAP-Elites in conjunction with VAEs enables the generation of a diverse set of playable levels not just for each individual game but also for the blended domain while illuminating game-specific regions of the blended latent space.
Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness
University of Science and Technology of China（中国科学技术大学）；Baidu Talent Intelligence Center（百度人才智库中心）；Rutgers, The State University of New Jersey（罗格斯大学新泽西州立大学）
Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
Center for Systems Biology Dresden（德累斯顿系统生物学中心）；Max-Planck Institute (CBG)（马克斯·普朗克分子细胞生物学与遗传学研究所）；School of Computer Science（计算机科学学院）；University of Birmingham（伯明翰大学）；Fondazione Human Technopole（人类技术基金会）
Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders: A Comparison Study
ETH Zurich（苏黎世联邦理工学院）；University of Zurich（苏黎世大学）；Stanford University（斯坦福大学）；Stanford Stroke Center（斯坦福中风中心）；Institute for Biomedical Engineering（生物医学工程研究所）
GM Score: Incorporating inter-class and intra-class generator diversity, discriminability of disentangled representation, and sample fidelity for evaluating GANs
School of Computer Engineering, KIIT Deemed to be University（KIIT 大学计算机工程学院）
GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Huazhong University of Science and Technology（华中科技大学）；Linköping University（林雪平大学）
Active Learning-Guided Seq2Seq Variational Autoencoder for Multi-target Inhibitor Generation
Barcelona Supercomputing Center (BSC)（巴塞罗那超级计算中心）；PhD program in Biotechnology, Faculty of Pharmacy and Food Sciences, University of Barcelona (UB)（巴塞罗那大学药学与食品科学系生物技术博士项目）；Alzheimer's Research UK Oxford Drug Discovery Institute, Centre for Medicines Discovery, Nuffield Department of Medicine, Oxford, UK（英国阿尔茨海默病研究奥德赛药物发现研究所、药物发现中心、医学系，牛津，英国）；Centre for Medicines Discovery, Nuffield Department of Medicine Research Building (NDMRB), University of Oxford, Oxford, UK（药物发现中心、医学系研究大楼（NDMRB）、牛津大学，牛津，英国）
Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search
Leiden Institute of Advanced Computer Science（莱顿高级计算机科学研究所）；Bonn-Rhein-Sieg University of Applied Sciences（波恩-莱茵-锡格应用科学大学）；Queen Mary University of London（伦敦玛丽女王大学）；SensiLab, Monash University（莫纳什大学SensiLab）
Vector Quantized-Elites: Unsupervised and Problem-Agnostic Quality-Diversity Optimization
Computational Intelligence Laboratory (CILab), Department of Mathematics, University of Patras（数学系计算智能实验室（CILab），帕特拉大学）；Laboratory of Automation and Robotics (LAR) in the Department of Electrical & Computer Engineering, University of Patras（电气与计算机工程系自动化与机器人实验室（LAR），帕特拉大学）
cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending
Department of Computer Science, University of Maryland, College Park, Maryland, USA（美国马里兰大学计算机科学系）；School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona, USA（亚利桑那州立大学计算与增强智能学院）
Dynamic User Interface Generation for Enhanced Human-Computer Interaction Using Variational Autoencoders
University of Southern California（南加州大学）；School of Visual Arts（视觉艺术学院）；Georgia Institute of Technology（佐治亚理工学院）；Carnegie Mellon University（卡内基梅隆大学）；New York University（纽约大学）
Controllable and Diverse Text Generation in E-commerce
University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Alibaba Group（阿里巴巴集团）；Zhejiang University（浙江大学）；University of Wisconsin, Madison（威斯康星大学麦迪逊分校）
在电子商业中，文本生成的一个关键挑战是在词的多样性和准确性（相关性）之间找到一个很好的折衷，以使生成的文本看起来更自然和人性化。为了提高生成结果的相关性，开发了条件文本生成器，使用输入关键字或属性来生成相应的文本。然而，以前的工作，不精细地控制自动生成的句子的多样性。例如，它不控制关键字的顺序，将更相关的放在第一位。此外，它没有明确控制多样性和准确性之间的平衡。为了解决这些问题，我们提出了一个细粒度的可控生成模型，称为~\textit{Apex}，它使用的算法借用自动控制（即，一个变种的\textit{proportional, integral, and derivative (PID) controller}），以精确地操纵生成的文本的多样性/准确性权衡。该算法被注入到一个条件变分自动编码器（CVAE），允许\textit{Apex}来控制（i）关键字在生成的句子中的顺序（以输入关键字及其顺序为条件），以及（ii）多样性和准确性之间的权衡。在真实数据集上的评价结果表明，该方法在多样性和相关性方面优于现有的生成模型。Apex目前被部署用于在中国最大的电子商业平台阿里巴巴旗下的淘宝上生成产品描述和商品推荐理由。A/B生产测试结果表明，与现有的生产描述方法相比，该方法提高了13.17%的点击率。对于项目推荐而言，与用户评论和没有评论的top-K项目推荐相比，它能够分别提高CTR 6.…
Recursive Variational Autoencoders for 3D Blood Vessel Generative Modeling
Consejo Nacional de Investigaciones Científicas y Técnicas（阿根廷国家科学与技术研究院）；Universidad Torcuato Di Tella（托科托迪塔拉大学）；Depto. Ing. Eléctrica y Computadoras, Universidad Nacional del Sur（国家南部大学电子工程与计算机系）
A Probabilistic Autoencoder for Type Ia Supernovae Spectral Time Series
University of California, Berkeley（加州大学伯克利分校）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；Sorbonne Université（索邦大学）；Université de Paris（巴黎大学）；University of Washington（华盛顿大学）
