VTubing, the practice of live streaming using virtual avatars, has gained worldwide popularity among streamers seeking to maintain anonymity. While previous research has primarily focused on the social and cultural aspects of VTubing, there is a noticeable lack of studies examining the practical challenges VTubers face in creating and operating their avatars. To address this gap, we surveyed VTubers' equipment and expanded the live-streaming design space by introducing six new dimensions related to avatar creation and control. Additionally, we conducted interviews with 16 professional VTubers to comprehensively explore their practices, strategies, and challenges throughout the VTubing process. Our findings reveal that VTubers face significant burdens compared to real-person streamers due to fragmented tools and the multi-tasking nature of VTubing, leading to unique workarounds. Finally, we summarize these challenges and propose design opportunities to improve the effectiveness and efficiency of VTubing.

Wind farms generate electricity from wind, offering a sustainable and eco-friendly power source.In wind farms, determining the positions of wind turbines is crucial for high energy production due to complex wake interactions.However, optimizing wind farm layouts for given wind conditions remains challenging.While existing methods try to solve the problem by training a surrogate model and employing optimization algorithms based on the model, these methods require a large number of simulations to obtain highly productive layouts, which is time-consuming in large-scale tasks.Furthermore, they mostly yield less diverse layouts, making the deployment of such layouts into real-world scenarios difficult.To address these challenges, we introduce a novel conditional generative modeling approach to find wind farm layouts that maximize energy production.Our method consists of four stages.First, we collect datasets that consist of layouts and their corresponding annual energy production (AEP).Then, we train a diffusion model conditioned on AEP and wind scenarios using the collected dataset.Specifically, we use a Graph Neural Network as the backbone for the denoising network to ensure permutation invariance.Next, we sample promising layouts from the trained diffusion model by conditioning with a high AEP and given wind scenario.We also introduce a local search algorithm, which enables us to adjust layouts that violate design constraints.Finally, we evaluate the generated layouts and augment the dataset.We repeat these processes iteratively to further optimize the layouts.Throughout these processes, we effectively generate highly productive and diverse wind farm layouts in a sample-efficient manner.Experimental results demonstrate that our approach outperforms state-of-the-art methods in maximizing energy production across various scenarios.

While federated learning leverages distributed client resources, it faces challenges due to heterogeneous client capabilities. This necessitates allocating models suited to clients' resources and careful parameter aggregation to accommodate this heterogeneity. We propose HypeMeFed, a novel federated learning framework for supporting client heterogeneity by combining a multi-exit network architecture with hypernetwork-based model weight generation. This approach aligns the feature spaces of heterogeneous model layers and resolves per-layer information disparity during weight aggregation. To practically realize HypeMeFed, we also propose a low-rank factorization approach to minimize computation and memory overhead associated with hypernetworks. Our evaluations on a real-world heterogeneous device testbed indicate that HypeMeFed enhances accuracy by 5.12% over FedAvg, reduces the hypernetwork memory requirements by 98.22%, and accelerates its operations by 1.86X compared to a naive hypernetwork approach. These results demonstrate HypeMeFed's effectiveness in leveraging and engaging heterogeneous clients for federated learning.

Predicting floods caused by the rise of the sea level is a critical task for preventing large scale catastrophes. Such predictions can potentially be made using a forecast of the sea level and a detailed model of the terrain. However, since available terrain datasets can easily exceed the size of the main memory of a standard computer, I/O (rather than internal computation time) can often become the bottleneck when computing such predictions. Thus to perform predictions efficiently we need an I/O-efficient approach, which minimizes the transfer of data blocks between main memory and disk. Given a terrain raster T and a sea-level forecast raster S of N cells each, we examine the problem of computing the water level of the induced flood for each cell in T. We introduce an I/O-efficient algorithm for this problem that uses O((N/B) logM/B (X/B)) I/Os after O((N/B) logM/B (N/B)) I/Os of preprocessing, where X is the number of local minima in T, and M and B are the size of main memory and data block, respectively. When X < M (which holds in practice) our algorithm requires optimal O(N/B) I/Os after preprocessing. We have implemented our algorithm and put considerable effort into engineering it. We present experiments that illustrate the efficiency and practicality of the algorithm, which is so efficient that work is underway to incorporate our results in the forecast services of the Danish Meteorological Institute.