Corporate financial news is pivotal for market decisions, but often overwhelms general audiences. While data videos effectively bridge this comprehension gap, their production remains a bottleneck for journalists. We present NewsVis, an authoring tool powered by Generative Artificial Intelligence (GenAI) that automates the transformation of unstructured narratives and raw financial datasets into professional data videos. Unlike generic models, our pipeline ensures factual accuracy through a domain-specific taxonomy of financial attributes and optimizes visual information presentation via a multimodal layout algorithm. Additionally, a human-in-the-loop interface empowers journalists to audit and calibrate generative outputs. Comprehensive quantitative and qualitative evaluations demonstrate that NewsVis significantly reduces production barriers while enhancing information accessibility for viewers.

Scientific discoveries increasingly rely on complex multimodal reasoning based on information-intensive scientific data and domain-specific expertise. Empowered by expert-level scientific benchmarks, scientific Multimodal Large Language Models (MLLMs) hold the potential to significantly enhance this discovery process in realistic workflows. However, current scientific benchmarks mostly focus on evaluating the knowledge understanding capabilities of MLLMs, leading to an inadequate assessment of their perception and reasoning abilities. To address this gap, we present the Scientists’ First Exam (SFE) benchmark, designed to evaluate the scientific cognitive capacities of MLLMs through three interconnected levels: scientific signal perception, scientific attribute understanding, scientific comparative reasoning. Specifically, SFE comprises 830 expert-verified VQA pairs across three question types, spanning 66 multimodal tasks across five high-value disciplines. Extensive experiments reveal that current state-of-the-art GPT-o3 and InternVL-3 achieve only 34.08% and 26.52% on SFE, highlighting significant room for MLLMs to improve in scientific realms. We hope the insights obtained in SFE will facilitate further developments in AI-enhanced scientific discoveries.

Music and visual arts are essential in children’s arts education, and their integration has garnered significant attention. Existing data analysis methods for exploring audio-visual correlations are limited. Yet, relevant research is necessary for innovating and promoting arts integration courses. In our work, we collected substantial volumes of music-inspired doodles created by children and interviewed education experts to comprehend the challenges they encountered in the relevant analysis. Based on the insights we obtained, we designed and constructed an interactive visualization system DoodleTunes. DoodleTunes integrates deep learning-driven methods for automatically annotating several types of data features. The visual designs of the system are based on a four-level analysis structure to construct a progressive workflow, facilitating data exploration and insight discovery between doodle images and corresponding music pieces. We evaluated the accuracy of our feature prediction results and collected usage feedback on DoodleTunes from five domain experts.