CASE: Confusion-Aware Skill Evolution for Frozen Multimodal Emotion Models
CASE maintains a sparse, self-evolving library of pair-specific EmotionSkills that externalize affective expertise from model parameters, enabling the learned expertise to be continuously refined and readily transferred across diverse frozen MLLM backbones.
Si-Yu Wu, Ze-Yu Liang, Ling-Hao Wang et al.
· 0 citations