AI 中文总结
研究旨在解决生成式人工智能中缺乏个性化情感理解等问题，提出EROS混合框架，结合符号推理与深度学习，利用大规模数据集发现情感规则等，通过可扩展记忆库实现个性化，实验表明其能有效引发目标情感反应并适应个体偏好，为相关AI系统奠定基础。
AI 中文摘要
情商使人类能够识别情绪、推断其原因、思考干预措施并改变环境以实现期望的情感状态。尽管人工智能最近取得了进展，但当前模型在理解、预测和个性化人类情感反应方面能力有限。本文介绍了情感增强生成系统（EROS），这是一个将符号推理与深度学习相结合的混合人工智能框架，通过视觉内容实现个性化情感增强。利用大规模图像-情感数据集，EROS发现可推广的情感规则，识别与情感相关的图像区域，并预测在保持场景语义的同时将情感反应导向期望目标的上下文感知视觉修改。为了考虑个体差异，EROS包含一个可扩展的记忆库，支持推理时的个性化而无需模型微调，产生可解释的情感概况并能快速适应新用户。在广泛的人类心理物理学实验中，EROS比现有最先进的大型多模态模型更有效地引发目标情感反应，同时适应个体情感偏好。EROS为能够理解、推理和增强人类认知状态的人工智能系统奠定了基础，在心理健康、自适应媒体、教育和人机交互等方面有潜在应用。
英文摘要
Emotional intelligence enables humans to recognize emotions, infer their causes, reason about interventions, and modify their environment to achieve desired affective states. Despite recent advances in artificial intelligence (AI), current models remain largely limited to generating realistic content or performing semantic reasoning, with little capacity for understanding, predicting, and personalizing human emotional responses. Here we introduce Emotion-augmented geneRatiOn System (EROS), a hybrid AI framework that integrates symbolic reasoning with deep learning to enable personalized emotion augmentation through visual content. Leveraging large-scale image-emotion datasets, EROS discovers generalizable affective rules, identifies emotion-relevant image regions, and predicts context-aware visual modifications that preserve scene semantics while steering emotional responses toward desired targets. To account for individual variability, EROS incorporates an expandable memory bank that supports inference-time personalization without model fine-tuning, yielding interpretable emotional profiles and rapid adaptation to new users. Across extensive human psychophysics experiments, EROS elicits target emotional responses more effectively than state-of-the-art large multimodal models while adapting to individual affective preferences. Beyond affective computing, EROS provides a foundation for AI systems that can understand, reason about, and augment human cognitive states, with potential applications in mental health, adaptive media, education, and human-computer interaction.
