In this paper, we present our solution for the semi-supervised learning track (MER-SEMI) in MER2025. We propose a comprehensive framework, grounded in the principle that "more is better," to construct a robust Mixture of Experts (MoE) emotion recognition system. Our approach integrates a diverse range of input modalities as independent experts, including novel signals such as knowledge from large Vision-Language Models (VLMs) and temporal Action Unit (AU) information. To effectively utilize unlabeled data, we introduce a consensus-based pseudo-labeling strategy, generating high-quality labels from the agreement between a baseline model and Gemini, which are then used in a two-stage training paradigm. Finally, we employ a multi-expert voting ensemble combined with a rule-based re-ranking process to correct prediction bias and better align the outputs with human preferences. Evaluated on the MER2025-SEMI challenge dataset, our method achieves an F1-score of 0.8772 on the test set, ranking 2nd in the track. Our code is available at https://github.com/zhuyjan/MER2025-MRAC25.
@article{arxiv.2508.06036,
title = {More Is Better: A MoE-Based Emotion Recognition Framework with Human Preference Alignment},
author = {Jun Xie and Yingjian Zhu and Feng Chen and Zhenghao Zhang and Xiaohui Fan and Hongzhu Yi and Xinming Wang and Chen Yu and Yue Bi and Zhaoran Zhao and Xiongjun Guan and Zhepeng Wang},
journal= {arXiv preprint arXiv:2508.06036},
year = {2025}
}