We present VibeSpace, a novel method for the fully unsupervised construction of interpretable embedding spaces applicable to arbitrary domains. Our approach automates costly data acquisition by leveraging the knowledge embedded in large language models (LLMs), facilitating similarity assessments between entities for meaningful positioning within vector spaces, while also enabling intelligent mappings between vector space representations of disparate domains through a novel form of cross-domain similarity analysis. First, we demonstrate that our data collection methodology yields comprehensive and rich datasets across multiple domains, including songs, books, and movies. We validate the reliability of the automatically generated data via cross-checks with domain-specific catalogues. Second, we show that our method generates single-domain embedding spaces that are separable by domain-specific features, providing a robust foundation for classification tasks, recommendation systems, and other downstream applications. These spaces can be interactively queried for semantic information about different regions in embedding spaces. Lastly, by exploiting the unique capabilities of current state-of-the-art large language models, we produce cross-domain mappings that capture contextual relationships between heterogeneous entities that may not be attainable through traditional methods. This approach facilitates the creation of embedding spaces of any domain, which circumvents the need to collect and calibrate sensitive user data and provides deeper insights and better interpretations of multi-domain data.

Abstract A key aspect of temporal domains is the ability to make predictions multiple time-steps into the future, a process known as multi-step forecasting (MSF). At the core of this process is selecting a forecasting strategy; however, with no existing frameworks to map out the space of strategies, practitioners are left with ad-hoc methods for strategy selection. In this work, we propose Stratify , a parameterised framework that addresses multi-step forecasting, unifying existing strategies and introducing novel, improved strategies. We evaluate Stratify on 18 benchmark datasets, five function classes, and short to long forecast horizons (10, 20, 40, 80) in the univariate setting. In over 84% of 1080 experiments, novel strategies in Stratify improved performance compared to all existing ones. Importantly, we find that no single strategy consistently outperforms others in all task settings, highlighting the need for practitioners to explore the Stratify space to carefully search and select forecasting strategies based on task-specific requirements. Our results are the most comprehensive benchmarking of known and novel forecasting strategies. We share the code ( https://github.com/zs18656/stratify_unifying_MSF ) to reproduce our results.

Wildfires affect many regions across the world. The accelerated progression of global warming has amplified their frequency and scale, deepening their impact on human life, the economy, and the environment. The temperature rise has been driving wildfires to behave unpredictably compared to those previously observed, challenging researchers and fire management agencies to understand the factors behind this behavioral change. Furthermore, this change has rendered fire personnel training outdated and lost its ability to adequately prepare personnel to respond to these new fires. Immersive visualization can play a key role in tackling the growing issue of wildfires. Therefore, this survey reviews various studies that use immersive and non-immersive data visualization techniques to depict wildfire behavior and train first responders and planners. This paper identifies the most useful characteristics of these systems. While these studies support knowledge creation for certain situations, there is still scope to comprehensively improve immersive systems to address the unforeseen dynamics of wildfires.