This paper introduces PuppetLine, an interactive storytelling system that translates natural language narratives into coordinated performances using tabletop robots. The system combines large language models with a constrained set of action and emotion primitives to generate physically executable and interpretable multi-robot motions. We describe the system design and report findings from a designer-centered user study examining how people interpret and reflect on robot enactments. The results provide formative insights into mapping narrative intent to embodied interaction and inform the design of narrative Swarm User Interfaces.

For question-answering (QA) tasks, in-context learning (ICL) enables language models (LMs) to generate responses without modifying their parameters by leveraging examples provided in the input. However, the effectiveness of ICL heavily depends on the availability of high-quality examples, which are often scarce due to data privacy constraints, annotation costs, and distribution disparities. A natural solution is to utilize examples stored on client devices, but existing approaches either require transmitting model parameters—incurring significant communication overhead—or fail to fully exploit local datasets, limiting their effectiveness. To address these challenges, we propose Federated In-Context Learning (Fed-ICL), a general framework that enhances ICL through an iterative, collaborative process. Fed-ICL progressively refines responses by leveraging multi-round interactions between clients and a central server, improving answer quality without the need to transmit model parameters. We establish theoretical guarantees for the convergence of Fed-ICL and conduct extensive experiments on standard QA benchmarks, demonstrating that our proposed approach achieves strong performance while maintaining low communication costs.

While Swarm User Interfaces (SUIs) have succeeded in enriching tangible interaction experiences, their limitations in autonomous action planning have hindered the potential for personalized and dynamic interaction generation in tabletop games. Based on the AI-Gadget Kit we developed, this paper explores how to integrate LLM-driven agents to enable SUIs to execute interaction tasks within tabletop games. After defining the design space of this kit, we elucidate the method for designing agents that can extend the meta-actions of SUIs to motion planning. Furthermore, we introduce an add-on prompt method that simplifies the design process for four interaction relationships in tabletop games. Lastly, we present an example that illustrates the potential of AI-Gadget Kit to construct personalized complex interactions in SUI tabletop games.

Despite the success of Quantum Neural Networks (QNNs) in decision-making systems, their fairness remains unexplored, as the focus primarily lies on accuracy. This work conducts a design space exploration, unveiling QNN unfairness, and highlighting the significant influence of QNN deployment and quantum noise on accuracy and fairness. To effectively navigate the vast QNN deployment design space, we propose JustQ, a framework for deploying fair and accurate QNNs on NISQ computers. It includes a complete NISQ error model, reinforcement learning-based deployment, and a flexible optimization objective incorporating both fairness and accuracy. Experimental results show JustQ outperforms previous methods, achieving superior accuracy and fairness. This work pioneers fair QNN design on NISQ computers, paving the way for future investigations.

The carbon footprint associated with large language models (LLMs) is a significant concern, encompassing emissions from their training, inference, experimentation, and storage processes, including operational and embodied carbon emissions. An essential aspect is accurately estimating the carbon impact of emerging LLMs even before their training, which heavily relies on GPU usage. Existing studies have reported the carbon footprint of LLM training, but only one tool, mlco2, can predict the carbon footprint of new neural networks prior to physical training. However, mlco2 has several serious limitations. It cannot extend its estimation to dense or mixture-of-experts (MoE) LLMs, disregards critical architectural parameters, focuses solely on GPUs, and cannot model embodied carbon footprints. Addressing these gaps, we introduce \textit{\carb}, an end-to-end carbon footprint projection model designed for both dense and MoE LLMs. Compared to mlco2, \carb~significantly enhances the accuracy of carbon footprint estimations for various LLMs. The source code is released at \url{https://github.com/SotaroKaneda/MLCarbon}.

Interpersonal conflicts are often more difficult to mediate when communicating remotely. The lack of social cues and external mediation makes it difficult for positive conflict behaviors to occur. To this end, robots have been shown to have the potential as mediators. In this paper, we attempt to discuss how to design appropriate bodily contact interactions for the different roles of a robot mediator so as to facilitate the effectiveness of its mediation. We first conduct a pilot interview to probe the potential roles and design elements of robot contact in this study. Then, we explore the relationship between these roles and design elements through a 16-participant design workshop. Finally, we analyze these findings and propose design suggestions for future robot mediator design.

Genealogy research is the study of family history using available resources such as historical records. Ancestry provides its customers with one of the world's largest online genealogical index with billions of records from a wide range of sources, including vital records such as birth and death certificates, census records, court and probate records among many others. Search at Ancestry aims to return relevant records from various record types, allowing our subscribers to build their family trees, research their family history, and make meaningful discoveries about their ancestors from diverse perspectives.

At Ancestry, we apply learning to rank algorithms to a new area to assist our customers in better understanding their family history. The foundation of our service is an extensive and unique collection of billions of historical records that we have digitized and indexed. Currently, our content collection includes 20 billion historical records. The record data consists of birth records, death records, marriage records, adoption records, census records, obituary records, among many others types. It is important for us to return relevant records from diversified record types in order to assist our customers to better understand their family history.