Automatic Algorithm Selection In Multi-agent Pathfinding
University of Alberta（阿尔伯塔大学）；Washington University in St. Louis（圣路易斯华盛顿大学）；Universidad Andres Bello（安德烈斯·贝略大学）；University of Southern California（南加州大学）
Devon Sigurdson, Vadim Bulitko, Sven Koenig, Carlos Hernandez, William Yeoh
In a multi-agent pathfinding (MAPF) problem, agents need to navigate from their start to their goal locations without colliding into each other. There are various MAPF algorithms, including Windowed Hierarchical Cooperative A*, Flow Annotated Replanning, and Bounded Multi-Agent A*. It is often the case that there is no a single algorithm that dominates all MAPF instances. Therefore, in this paper, we investigate the use of deep learning to automatically select the best MAPF algorithm from a portfolio of algorithms for a given MAPF problem instance. Empirical results show that our automatic algorithm selection approach, which uses an off-the-shelf convolutional neural network, is able to outperform any individual MAPF algorithm in our portfolio.
Automatic Combination of Sample Selection Strategies for Few-Shot Learning
Faculty of Information Technology, Brno University of Technology（布拉格技术学院，布拉格技术大学）；Kempelen Institute of Intelligent Technologies（智能技术研究所）；Eindhoven University of Technology（埃因霍温技术大学）
VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
University of Waterloo（滑铁卢大学）；University of Melbourne（墨尔本大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；MBZUAI（马克斯·普朗克智能系统研究所）；Macquarie University（麦考瑞大学）
A Learning-Based Method for Automatic Operator Selection in the Fanoos XAI System
Carnegie Mellon University（卡内基梅隆大学）
我们描述了Fanoos XAI系统的扩展[Bayani et al 2022]，它使系统能够学习采取适当的行动，以满足用户对或多或少抽象的描述的请求。具体来说，被分析系统的描述是以状态存储的，为了使描述或多或少地抽象，Fanoos从一个大型库中选择一个操作符应用于状态并生成新的描述。以前的工作主要使用手写的方法来选择操作员;目前的工作允许Fanoos利用经验来学习最佳操作员，以应用于特定情况，平衡探索和开发，利用专家的见解，并利用当前状态和过去状态之间的相似性。此外，为了引导学习过程（即，就像在课程学习中一样），我们描述了一个我们实现的模拟用户;这个模拟允许Fanoos获得一般的见解，从而实现合理的行动过程，这些见解以后可以通过与真实用户的经验进行改进，而不是完全从头开始与人类交互。实现本文中描述的方法的代码可以在https：//github/DBay-ani/Operator_Selection_Learning_Extensions_For_Fanoos上找到。
A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
University of Missouri–Kansas City（密苏里大学堪萨斯城分校）；U. S. Naval Research Laboratory（美国海军研究实验室）；Lamar University（拉马尔大学）；University of Florida（佛罗里达大学）；University of Texas Rio Grande Valley（德克萨斯大学里奥格兰德河谷分校）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Meta AI；Rochester Institute of Technology（罗切斯特理工学院）
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
ShanghaiTech University（上海科技大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Meituan（美团）；Alibaba Group（阿里巴巴集团）；The Hong Kong University of Science and Technology（香港科技大学）
A Novel Biologically Mechanism-Based Visual Cognition Model--Automatic Extraction of Semantics, Formation of Integrated Concepts and Re-selection Features for Ambiguity
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Institute of Applied Mathematics, Academy of Mathematics and Systems Science, Chinese Academy of Science（中国科学院数学与系统科学研究院应用数学研究所）
Automatic Unsupervised Ensemble Outlier Model Selection--Extended Version
Department of Software Engineering, FPT University, Vietnam（FPT大学软件工程系）；Department of Information Technology, Can Tho University of Technology, Vietnam（胡志明市技术大学信息科技系）；School of Business, RMIT University, Vietnam（RMIT大学商学院）；Department of Computer Science, Aalborg University, Denmark（阿阿尔堡大学计算机科学系）；School of Data Science and Engineering, East China Normal University, China（华东师范大学数据科学与工程学院）
Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration
Platform Lab, College of Information Technology, Soongsil University, Seoul, South Korea（平台实验室，信息科技学院，顺斯大学，首尔，韩国）；Computing Systems Lab, College of Information Technology, Soongsil University, Seoul, South Korea（计算系统实验室，信息科技学院，顺斯大学，首尔，韩国）
Selection Hyper-heuristics Can Automatically Adjust the Learning Period to Optimally Solve Pseudo-Boolean Problems
Laboratoire d’Informatique (LIX), CNRS, École Polytechnique, Institut Polytechnique de Paris（信息实验室（LIX），法国国家科学研究中心，巴黎高等理工学院，巴黎理工学院）；Department of Computer Science and Engineering, Southern University of Science and Technology（计算机科学与工程系，南方科技大学）；School of Computing & Communications, Lancaster University Leipzig（计算与通信学院，莱斯特大学莱比锡分校）
