Researchers posted a preprint describing a multimodal foundation model that uses language guidance to handle brain signal analysis without task-specific retraining. The approach is presented as supporting zero-shot and multi-task settings, addressing limited generalization in existing end-to-end and pre-trained models. The work appears on arXiv under cs.AI and cs.LG.
A new arXiv preprint studies whether multi-task learning can improve predictive process monitoring, which forecasts how ongoing organizational processes will unfold so information systems can support proactive analysis rather than just execution. The work situates itself within deep learning approaches that have already raised prediction accuracy in this area, and explores the potential of training related prediction tasks jointly.
A new arXiv paper introduces a multi-task surrogate model that combines physical constraints with machine learning to simulate the Martian nightside thermosphere. The problem is difficult because direct measurements are sparse and transport, magnetic, and seasonal effects interact strongly, so purely data-driven approaches can produce unphysical outputs such as reversed density trends. Embedding physics into the training process aims to keep the model's predictions consistent with known atmospheric behavior.