AI 中文总结
针对现有情感智能多模态模型忽略任务协同的问题，研究人员提出统一多模态情感模型OneEmo，构建EmoWorld-130K数据集并采用Emo-Chord强化学习策略，其性能优于同规模基线模型，参数远少于商业模型且结果具竞争力。
AI 中文摘要
多模态大语言模型（MLLMs）已展现出卓越的情感智能能力，但现有研究大多聚焦于特定任务的专业化，常忽略任务间的协同性，未充分挖掘潜在的推理潜力。为填补这一空白，我们提出OneEmo，一款能掌握情感感知、理解与交互的通用情感智能体。为此，我们首先构建了EmoWorld-130K数据集，该数据集通过人机协作流程将专业化的情感知识提炼为明确的推理轨迹；对该语料库进行监督微调后，发现多任务学习能带来显著的相互增益。其次，为充分释放潜在推理潜力，我们提出Emo-Chord，一种通过统一多任务奖励分配来稳定优化过程的新型强化学习策略。大量实验表明，OneEmo在多数基准测试中，与规模相近的基线模型相比达到了最优性能；值得注意的是，尽管OneEmo的参数规模远小于商业模型，却能输出极具竞争力的结果。本研究为构建更可靠、可解释的情感计算模型铺平了道路，代码可访问该https URL获取。
英文摘要
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in emotional intelligence. However, prevailing research predominantly focuses on task-specific specialization, often neglecting inter-task synergy and leaving latent reasoning potential underexplored. To bridge this gap, we introduce OneEmo, a unified affective generalist capable of mastering emotion perception, comprehension, and interaction. For this purpose, we first construct EmoWorld-130K, a comprehensive dataset that distills specialized affective knowledge into explicit reasoning trajectories via a human-in-the-loop workflow. Supervised fine-tuning on this corpus reveals significant mutual benefits derived from multi-task learning. Second, to fully unlock the latent reasoning potential, we propose Emo-Chord, a novel reinforcement learning strategy that stabilizes optimization through unified multi-task reward allocation. Extensive experiments demonstrate that OneEmo achieves state-of-the-art performance against similarly sized baselines across most benchmarks. Notably, despite having significantly fewer parameters than commercial models, OneEmo delivers highly competitive results. This paper paves the way for more reliable and interpretable affective computing. The code is available at https://github.com/waHAHJIAHAO/OneEmo.
